# NIPS 2017

The most popular implementations from this conference
##### GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
Generative Adversarial Networks (GANs) excel at creating realistic images with complex models for which maximum likelihood is infeasible. However, the convergence of GAN training has still not been proved.
4,444
##### Improved Training of Wasserstein GANs
Generative Adversarial Networks (GANs) are powerful generative models, but suffer from training instability. The recently proposed Wasserstein GAN (WGAN) makes progress toward stable training of GANs, but sometimes can still generate only low-quality samples or fail to converge.
1,372
##### Unsupervised Image-to-Image Translation Networks
Unsupervised image-to-image translation aims at learning a joint distribution of images in different domains by using images from the marginal distributions in individual domains. Since there exists an infinite set of joint distributions that can arrive the given marginal distributions, one could infer nothing about the joint distribution from the marginal distributions without additional assumptions.
1,183
##### GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
Generative Adversarial Networks (GANs) excel at creating realistic images with complex models for which maximum likelihood is infeasible. However, the convergence of GAN training has still not been proved.
1,136
##### Toward Multimodal Image-to-Image Translation
Many image-to-image translation problems are ambiguous, as a single input image may correspond to multiple possible outputs. Our proposed method encourages bijective consistency between the latent encoding and output modes.
774
##### Inductive Representation Learning on Large Graphs
Low-dimensional embeddings of nodes in large graphs have proved extremely useful in a variety of prediction tasks, from content recommendation to identifying protein functions. However, most existing approaches require that all nodes in the graph are present during training of the embeddings; these previous approaches are inherently transductive and do not naturally generalize to unseen nodes.
509
##### Improved Training of Wasserstein GANs
Generative Adversarial Networks (GANs) are powerful generative models, but suffer from training instability. The recently proposed Wasserstein GAN (WGAN) makes progress toward stable training of GANs, but sometimes can still generate only low-quality samples or fail to converge.
425
##### Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments
We explore deep reinforcement learning methods for multi-agent domains. We begin by analyzing the difficulty of traditional algorithms in the multi-agent case: Q-learning is challenged by an inherent non-stationarity of the environment, while policy gradient suffers from a variance that increases as the number of agents grows.
407
##### Universal Style Transfer via Feature Transforms
Existing feed-forward based methods, while enjoying the inference efficiency, are mainly limited by inability of generalizing to unseen styles or compromised visual quality. The whitening and coloring transforms reflect a direct matching of feature covariance of the content image to a given style image, which shares similar spirits with the optimization of Gram matrix based cost in neural style transfer.
338
##### GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
Generative Adversarial Networks (GANs) excel at creating realistic images with complex models for which maximum likelihood is infeasible. However, the convergence of GAN training has still not been proved.
215
##### GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
Generative Adversarial Networks (GANs) excel at creating realistic images with complex models for which maximum likelihood is infeasible. However, the convergence of GAN training has still not been proved.
205
##### Universal Style Transfer via Feature Transforms
Existing feed-forward based methods, while enjoying the inference efficiency, are mainly limited by inability of generalizing to unseen styles or compromised visual quality. The whitening and coloring transforms reflect a direct matching of feature covariance of the content image to a given style image, which shares similar spirits with the optimization of Gram matrix based cost in neural style transfer.
203
##### GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
Generative Adversarial Networks (GANs) excel at creating realistic images with complex models for which maximum likelihood is infeasible. However, the convergence of GAN training has still not been proved.
202
##### One-Sided Unsupervised Domain Mapping
The goal is to learn a mapping $G_{AB}$ that translates a sample in $A$ to the analog sample in $B$. In this work, we present a method of learning $G_{AB}$ without learning $G_{BA}$.
136
##### Universal Style Transfer via Feature Transforms
Existing feed-forward based methods, while enjoying the inference efficiency, are mainly limited by inability of generalizing to unseen styles or compromised visual quality. The whitening and coloring transforms reflect a direct matching of feature covariance of the content image to a given style image, which shares similar spirits with the optimization of Gram matrix based cost in neural style transfer.
126
##### Working hard to know your neighbor's margins: Local descriptor learning loss
We introduce a novel loss for learning local feature descriptors which is inspired by the Lowe's matching criterion for SIFT. We show that the proposed loss that maximizes the distance between the closest positive and closest negative patch in the batch is better than complex regularization methods; it works well for both shallow and deep convolution network architectures.
120
##### Bayesian Optimization with Gradients
Bayesian optimization has been successful at global optimization of expensive-to-evaluate multimodal objective functions. However, unlike most optimization methods, Bayesian optimization typically does not use derivative information.
114
##### Train longer, generalize better: closing the generalization gap in large batch training of neural networks
Following this hypothesis we conducted experiments to show empirically that the "generalization gap" stems from the relatively small number of updates rather than the batch size, and can be completely eliminated by adapting the training regime used. We further investigate different techniques to train models in the large-batch regime and present a novel algorithm named "Ghost Batch Normalization" which enables significant decrease in the generalization gap without increasing the number of updates.
109
##### InfoGAIL: Interpretable Imitation Learning from Visual Demonstrations
The goal of imitation learning is to mimic expert behavior without access to an explicit reward signal. Expert demonstrations provided by humans, however, often show significant variability due to latent factors that are typically not explicitly modeled.
108
##### Learning Combinatorial Optimization Algorithms over Graphs
The design of good heuristics or approximation algorithms for NP-hard combinatorial optimization problems often requires significant specialized knowledge and trial-and-error. Can we automate this challenging, tedious process, and learn the algorithms instead?
107
##### Task-based End-to-end Model Learning in Stochastic Optimization
With the increasing popularity of machine learning techniques, it has become common to see prediction algorithms operating within some larger process. However, the criteria by which we train these algorithms often differ from the ultimate criteria on which we evaluate them.
97
##### Improved Training of Wasserstein GANs
Generative Adversarial Networks (GANs) are powerful generative models, but suffer from training instability. The recently proposed Wasserstein GAN (WGAN) makes progress toward stable training of GANs, but sometimes can still generate only low-quality samples or fail to converge.
97
##### MMD GAN: Towards Deeper Understanding of Moment Matching Network
Although some theoretical guarantees of MMD have been studied, the empirical performance of GMMN is still not as competitive as that of GAN on challenging and large benchmark datasets. In this paper, we propose to improve both the model expressiveness of GMMN and its computational efficiency by introducing adversarial kernel learning techniques, as the replacement of a fixed Gaussian kernel in the original GMMN.
81
##### A-NICE-MC: Adversarial Training for MCMC
We propose A-NICE-MC, a novel method to train flexible parametric Markov chain kernels to produce samples with desired properties. First, we propose an efficient likelihood-free adversarial training method to train a Markov chain and mimic a given data distribution.
78
##### Neural Discrete Representation Learning
Learning useful representations without supervision remains a key challenge in machine learning. In this paper, we propose a simple yet powerful generative model that learns such discrete representations.
61
##### Differentiable Learning of Logical Rules for Knowledge Base Reasoning
We propose a framework, Neural Logic Programming, that combines the parameter and structure learning of first-order logical rules in an end-to-end differentiable model. We design a neural controller system that learns to compose these operations.
60
##### The Neural Hawkes Process: A Neurally Self-Modulating Multivariate Point Process
Many events occur in the world. Some event types are stochastically excited or inhibited---in the sense of having their probabilities elevated or decreased---by patterns in the sequence of previous events.
53
##### Hybrid Reward Architecture for Reinforcement Learning
One of the main challenges in reinforcement learning (RL) is generalisation. In typical deep RL methods this is achieved by approximating the optimal value function with a low-dimensional representation using a deep network.
48
##### From Parity to Preference-based Notions of Fairness in Classification
The adoption of automated, data-driven decision making in an ever expanding range of applications has raised concerns about its potential unfairness towards certain social groups. In this context, a number of recent studies have focused on defining, detecting, and removing unfairness from data-driven decision systems.
46
##### Predicting Organic Reaction Outcomes with Weisfeiler-Lehman Network
The prediction of organic reaction outcomes is a fundamental problem in computational chemistry. Since a reaction may involve hundreds of atoms, fully exploring the space of possible transformations is intractable.
45
##### Safe Model-based Reinforcement Learning with Stability Guarantees
Reinforcement learning is a powerful paradigm for learning optimal policies from experimental data. However, to find optimal policies, most reinforcement learning algorithms explore all possible actions, which may be harmful for real-world systems.
44
##### Masked Autoregressive Flow for Density Estimation
Autoregressive models are among the best performing neural density estimators. By constructing a stack of autoregressive models, each modelling the random numbers of the next model in the stack, we obtain a type of normalizing flow suitable for density estimation, which we call Masked Autoregressive Flow.
42
##### Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results
To overcome this problem, we propose Mean Teacher, a method that averages model weights instead of label predictions. Without changing the network architecture, Mean Teacher achieves an error rate of 4.35% on SVHN with 250 labels, outperforming Temporal Ensembling trained with 1000 labels.
41
##### Improved Training of Wasserstein GANs
Generative Adversarial Networks (GANs) are powerful generative models, but suffer from training instability. The recently proposed Wasserstein GAN (WGAN) makes progress toward stable training of GANs, but sometimes can still generate only low-quality samples or fail to converge.
38
##### Improved Training of Wasserstein GANs
Generative Adversarial Networks (GANs) are powerful generative models, but suffer from training instability. The recently proposed Wasserstein GAN (WGAN) makes progress toward stable training of GANs, but sometimes can still generate only low-quality samples or fail to converge.
28
##### InfoGAIL: Interpretable Imitation Learning from Visual Demonstrations
The goal of imitation learning is to mimic expert behavior without access to an explicit reward signal. Expert demonstrations provided by humans, however, often show significant variability due to latent factors that are typically not explicitly modeled.
23
##### InfoGAIL: Interpretable Imitation Learning from Visual Demonstrations
The goal of imitation learning is to mimic expert behavior without access to an explicit reward signal. Expert demonstrations provided by humans, however, often show significant variability due to latent factors that are typically not explicitly modeled.
19
##### Generalization Properties of Learning with Random Features
We study the generalization properties of ridge regression with random features in the statistical learning framework. We show for the first time that $O(1/\sqrt{n})$ learning bounds can be achieved with only $O(\sqrt{n}\log n)$ random features rather than $O({n})$ as suggested by previous results.
17
##### Federated Multi-Task Learning
Federated learning poses new statistical and systems challenges in training machine learning models over distributed networks of devices. In this work, we show that multi-task learning is naturally suited to handle the statistical challenges of this setting, and propose a novel systems-aware optimization method, MOCHA, that is robust to practical systems issues.
16
##### FALKON: An Optimal Large Scale Kernel Method
They rely on solid functional analytic foundations and enjoy optimal statistical properties. In this paper, we take a substantial step in scaling up kernel methods, proposing FALKON, a novel algorithm that allows to efficiently process millions of points.
16
##### Improved Training of Wasserstein GANs
Generative Adversarial Networks (GANs) are powerful generative models, but suffer from training instability. The recently proposed Wasserstein GAN (WGAN) makes progress toward stable training of GANs, but sometimes can still generate only low-quality samples or fail to converge.
14
##### Streaming Weak Submodularity: Interpreting Neural Networks on the Fly
In many machine learning applications, it is important to explain the predictions of a black-box classifier. For example, why does a deep neural network assign an image to a particular class?
14
##### Controllable Invariance through Adversarial Feature Learning
Learning meaningful representations that maintain the content necessary for a particular task while filtering away detrimental variations is a problem of great interest in machine learning. In this paper, we tackle the problem of learning representations invariant to a specific factor or trait of data.
12
##### Overcoming Catastrophic Forgetting by Incremental Moment Matching
Catastrophic forgetting is a problem of neural networks that loses the information of the first task after training the second task. Here, we propose a method, i.e. incremental moment matching (IMM), to resolve this problem.
11
##### Gradient descent GAN optimization is locally stable
Despite the growing prominence of generative adversarial networks (GANs), optimization in GANs is still a poorly understood topic. In this paper, we analyze the "gradient descent" form of GAN optimization i.e., the natural setting where we simultaneously take small gradient steps in both generator and discriminator parameters.
11
##### Universal Style Transfer via Feature Transforms
Existing feed-forward based methods, while enjoying the inference efficiency, are mainly limited by inability of generalizing to unseen styles or compromised visual quality. The whitening and coloring transforms reflect a direct matching of feature covariance of the content image to a given style image, which shares similar spirits with the optimization of Gram matrix based cost in neural style transfer.
11
##### GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
Generative Adversarial Networks (GANs) excel at creating realistic images with complex models for which maximum likelihood is infeasible. However, the convergence of GAN training has still not been proved.
10
##### The Numerics of GANs
In this paper, we analyze the numerics of common algorithms for training Generative Adversarial Networks (GANs). Using the formalism of smooth two-player games we analyze the associated gradient vector field of GAN training objectives.
9
##### Improved Training of Wasserstein GANs
Generative Adversarial Networks (GANs) are powerful generative models, but suffer from training instability. The recently proposed Wasserstein GAN (WGAN) makes progress toward stable training of GANs, but sometimes can still generate only low-quality samples or fail to converge.
9
##### #Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learning
In this work, we describe a surprising finding: a simple generalization of the classic count-based approach can reach near state-of-the-art performance on various high-dimensional and/or continuous deep RL benchmarks. We find that simple hash functions can achieve surprisingly good results on many challenging tasks.
9
##### Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results
To overcome this problem, we propose Mean Teacher, a method that averages model weights instead of label predictions. Without changing the network architecture, Mean Teacher achieves an error rate of 4.35% on SVHN with 250 labels, outperforming Temporal Ensembling trained with 1000 labels.
7
##### Practical Hash Functions for Similarity Estimation and Dimensionality Reduction
We consider mixed tabulation hashing of Dahlgaard et al.[FOCS'15] which was proved to perform like a truly random hash function in many applications, including OPH. We find that mixed tabulation hashing is almost as fast as the multiply-mod-prime scheme ax+b mod p. Mutiply-mod-prime is guaranteed to work well on sufficiently random data, but we demonstrate that in the above applications, it can lead to bias and poor concentration on both real-world and synthetic data.
6
##### Hindsight Experience Replay
Dealing with sparse rewards is one of the biggest challenges in Reinforcement Learning (RL). We present a novel technique called Hindsight Experience Replay which allows sample-efficient learning from rewards which are sparse and binary and therefore avoid the need for complicated reward engineering.
5
$\ell^2$
##### Improved Training of Wasserstein GANs
Generative Adversarial Networks (GANs) are powerful generative models, but suffer from training instability. The recently proposed Wasserstein GAN (WGAN) makes progress toward stable training of GANs, but sometimes can still generate only low-quality samples or fail to converge.
5
##### NeuralFDR: Learning Discovery Thresholds from Hypothesis Features
For example, in genetic association studies, each hypothesis tests the correlation between a variant and the trait. We have a rich set of features for each variant (e.g. its location, conservation, epigenetics etc.)
5
##### On Structured Prediction Theory with Calibrated Convex Surrogate Losses
We provide novel theoretical insights on structured prediction in the context of efficient convex surrogate loss minimization with consistency guarantees. For any task loss, we construct a convex surrogate that can be optimized via stochastic gradient descent and we prove tight bounds on the so-called "calibration function" relating the excess surrogate risk to the actual risk.
4
##### Parallel Streaming Wasserstein Barycenters
Our method is even robust to nonstationary input distributions and produces a barycenter estimate that tracks the input measures over time. Finally, we demonstrate the practical effectiveness of our method, both in tracking moving distributions on a sphere, as well as in a large-scale Bayesian inference task.
4
##### The Numerics of GANs
In this paper, we analyze the numerics of common algorithms for training Generative Adversarial Networks (GANs). Using the formalism of smooth two-player games we analyze the associated gradient vector field of GAN training objectives.
3
##### Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments
We explore deep reinforcement learning methods for multi-agent domains. We begin by analyzing the difficulty of traditional algorithms in the multi-agent case: Q-learning is challenged by an inherent non-stationarity of the environment, while policy gradient suffers from a variance that increases as the number of agents grows.
3
##### Unifying PAC and Regret: Uniform PAC Bounds for Episodic Reinforcement Learning
Statistical performance bounds for reinforcement learning (RL) algorithms can be critical for high-stakes applications like healthcare. This paper introduces a new framework for theoretically measuring the performance of such algorithms called Uniform-PAC, which is a strengthening of the classical Probably Approximately Correct (PAC) framework.
3
##### Improved Training of Wasserstein GANs
Generative Adversarial Networks (GANs) are powerful generative models, but suffer from training instability. The recently proposed Wasserstein GAN (WGAN) makes progress toward stable training of GANs, but sometimes can still generate only low-quality samples or fail to converge.
3
##### A framework for Multi-A(rmed)/B(andit) testing with online FDR control
We propose an alternative framework to existing setups for controlling false alarms when multiple A/B tests are run over time. This setup arises in many practical applications, e.g. when pharmaceutical companies test new treatment options against control pills for different diseases, or when internet companies test their default webpages versus various alternatives over time.
3
##### Scalable Variational Inference for Dynamical Systems
That is why, despite the high computational cost, numerical integration is still the gold standard in many applications. Using an existing gradient matching approach, we propose a scalable variational inference framework which can infer states and parameters simultaneously, offers computational speedups, improved accuracy and works well even under model misspecifications in a partially observable system.
2
##### Pixels to Graphs by Associative Embedding
Graphs are a useful abstraction of image content. Not only can graphs represent details about individual objects in a scene but they can capture the interactions between pairs of objects.
2
##### Hindsight Experience Replay
Dealing with sparse rewards is one of the biggest challenges in Reinforcement Learning (RL). We present a novel technique called Hindsight Experience Replay which allows sample-efficient learning from rewards which are sparse and binary and therefore avoid the need for complicated reward engineering.
2
##### Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments
We explore deep reinforcement learning methods for multi-agent domains. We begin by analyzing the difficulty of traditional algorithms in the multi-agent case: Q-learning is challenged by an inherent non-stationarity of the environment, while policy gradient suffers from a variance that increases as the number of agents grows.
2
##### Imagination-Augmented Agents for Deep Reinforcement Learning
We introduce Imagination-Augmented Agents (I2As), a novel architecture for deep reinforcement learning combining model-free and model-based aspects. In contrast to most existing model-based reinforcement learning and planning methods, which prescribe how a model should be used to arrive at a policy, I2As learn to interpret predictions from a learned environment model to construct implicit plans in arbitrary ways, by using the predictions as additional context in deep policy networks.
1
##### GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
Generative Adversarial Networks (GANs) excel at creating realistic images with complex models for which maximum likelihood is infeasible. However, the convergence of GAN training has still not been proved.
1
##### Improved Training of Wasserstein GANs
Generative Adversarial Networks (GANs) are powerful generative models, but suffer from training instability. The recently proposed Wasserstein GAN (WGAN) makes progress toward stable training of GANs, but sometimes can still generate only low-quality samples or fail to converge.
1
##### Improved Training of Wasserstein GANs
Generative Adversarial Networks (GANs) are powerful generative models, but suffer from training instability. The recently proposed Wasserstein GAN (WGAN) makes progress toward stable training of GANs, but sometimes can still generate only low-quality samples or fail to converge.
1
##### Thinking Fast and Slow with Deep Learning and Tree Search
Sequential decision making problems, such as structured prediction, robotic control, and game playing, require a combination of planning policies and generalisation of those plans. In this paper, we present Expert Iteration (ExIt), a novel reinforcement learning algorithm which decomposes the problem into separate planning and generalisation tasks.
1
##### Universal Style Transfer via Feature Transforms
Existing feed-forward based methods, while enjoying the inference efficiency, are mainly limited by inability of generalizing to unseen styles or compromised visual quality. The whitening and coloring transforms reflect a direct matching of feature covariance of the content image to a given style image, which shares similar spirits with the optimization of Gram matrix based cost in neural style transfer.
1
##### Universal Style Transfer via Feature Transforms
Existing feed-forward based methods, while enjoying the inference efficiency, are mainly limited by inability of generalizing to unseen styles or compromised visual quality. The whitening and coloring transforms reflect a direct matching of feature covariance of the content image to a given style image, which shares similar spirits with the optimization of Gram matrix based cost in neural style transfer.
1
##### Neural Discrete Representation Learning
Learning useful representations without supervision remains a key challenge in machine learning. In this paper, we propose a simple yet powerful generative model that learns such discrete representations.
0
##### Toward Multimodal Image-to-Image Translation
Many image-to-image translation problems are ambiguous, as a single input image may correspond to multiple possible outputs. Our proposed method encourages bijective consistency between the latent encoding and output modes.
0
##### Hindsight Experience Replay
Dealing with sparse rewards is one of the biggest challenges in Reinforcement Learning (RL). We present a novel technique called Hindsight Experience Replay which allows sample-efficient learning from rewards which are sparse and binary and therefore avoid the need for complicated reward engineering.
0
##### Hindsight Experience Replay
Dealing with sparse rewards is one of the biggest challenges in Reinforcement Learning (RL). We present a novel technique called Hindsight Experience Replay which allows sample-efficient learning from rewards which are sparse and binary and therefore avoid the need for complicated reward engineering.
0
##### Unsupervised Image-to-Image Translation Networks
Unsupervised image-to-image translation aims at learning a joint distribution of images in different domains by using images from the marginal distributions in individual domains. Since there exists an infinite set of joint distributions that can arrive the given marginal distributions, one could infer nothing about the joint distribution from the marginal distributions without additional assumptions.
0
##### Imagination-Augmented Agents for Deep Reinforcement Learning
We introduce Imagination-Augmented Agents (I2As), a novel architecture for deep reinforcement learning combining model-free and model-based aspects. In contrast to most existing model-based reinforcement learning and planning methods, which prescribe how a model should be used to arrive at a policy, I2As learn to interpret predictions from a learned environment model to construct implicit plans in arbitrary ways, by using the predictions as additional context in deep policy networks.
0
##### A PAC-Bayesian Analysis of Randomized Learning with Application to Stochastic Gradient Descent
We study the generalization error of randomized learning algorithms -- focusing on stochastic gradient descent (SGD) -- using a novel combination of PAC-Bayes and algorithmic stability. This inspires an adaptive sampling algorithm for SGD that optimizes the posterior at runtime.
0
##### Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments
We explore deep reinforcement learning methods for multi-agent domains. We begin by analyzing the difficulty of traditional algorithms in the multi-agent case: Q-learning is challenged by an inherent non-stationarity of the environment, while policy gradient suffers from a variance that increases as the number of agents grows.
0
##### Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments
We explore deep reinforcement learning methods for multi-agent domains. We begin by analyzing the difficulty of traditional algorithms in the multi-agent case: Q-learning is challenged by an inherent non-stationarity of the environment, while policy gradient suffers from a variance that increases as the number of agents grows.
0
##### Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments
We explore deep reinforcement learning methods for multi-agent domains. We begin by analyzing the difficulty of traditional algorithms in the multi-agent case: Q-learning is challenged by an inherent non-stationarity of the environment, while policy gradient suffers from a variance that increases as the number of agents grows.
0
##### Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments
We explore deep reinforcement learning methods for multi-agent domains. We begin by analyzing the difficulty of traditional algorithms in the multi-agent case: Q-learning is challenged by an inherent non-stationarity of the environment, while policy gradient suffers from a variance that increases as the number of agents grows.
0
##### Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments
We explore deep reinforcement learning methods for multi-agent domains. We begin by analyzing the difficulty of traditional algorithms in the multi-agent case: Q-learning is challenged by an inherent non-stationarity of the environment, while policy gradient suffers from a variance that increases as the number of agents grows.
0
##### Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments
We explore deep reinforcement learning methods for multi-agent domains. We begin by analyzing the difficulty of traditional algorithms in the multi-agent case: Q-learning is challenged by an inherent non-stationarity of the environment, while policy gradient suffers from a variance that increases as the number of agents grows.
0
##### Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments
We explore deep reinforcement learning methods for multi-agent domains. We begin by analyzing the difficulty of traditional algorithms in the multi-agent case: Q-learning is challenged by an inherent non-stationarity of the environment, while policy gradient suffers from a variance that increases as the number of agents grows.
0
##### Working hard to know your neighbor's margins: Local descriptor learning loss
We introduce a novel loss for learning local feature descriptors which is inspired by the Lowe's matching criterion for SIFT. We show that the proposed loss that maximizes the distance between the closest positive and closest negative patch in the batch is better than complex regularization methods; it works well for both shallow and deep convolution network architectures.
0
##### GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
Generative Adversarial Networks (GANs) excel at creating realistic images with complex models for which maximum likelihood is infeasible. However, the convergence of GAN training has still not been proved.
0
##### GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
Generative Adversarial Networks (GANs) excel at creating realistic images with complex models for which maximum likelihood is infeasible. However, the convergence of GAN training has still not been proved.
0
##### Improved Training of Wasserstein GANs
Generative Adversarial Networks (GANs) are powerful generative models, but suffer from training instability. The recently proposed Wasserstein GAN (WGAN) makes progress toward stable training of GANs, but sometimes can still generate only low-quality samples or fail to converge.
0
##### Improved Training of Wasserstein GANs
Generative Adversarial Networks (GANs) are powerful generative models, but suffer from training instability. The recently proposed Wasserstein GAN (WGAN) makes progress toward stable training of GANs, but sometimes can still generate only low-quality samples or fail to converge.
0
##### Improved Training of Wasserstein GANs
Generative Adversarial Networks (GANs) are powerful generative models, but suffer from training instability. The recently proposed Wasserstein GAN (WGAN) makes progress toward stable training of GANs, but sometimes can still generate only low-quality samples or fail to converge.
0
##### Improved Training of Wasserstein GANs
Generative Adversarial Networks (GANs) are powerful generative models, but suffer from training instability. The recently proposed Wasserstein GAN (WGAN) makes progress toward stable training of GANs, but sometimes can still generate only low-quality samples or fail to converge.
0
##### Improved Training of Wasserstein GANs
Generative Adversarial Networks (GANs) are powerful generative models, but suffer from training instability. The recently proposed Wasserstein GAN (WGAN) makes progress toward stable training of GANs, but sometimes can still generate only low-quality samples or fail to converge.
0
##### Improved Training of Wasserstein GANs
Generative Adversarial Networks (GANs) are powerful generative models, but suffer from training instability. The recently proposed Wasserstein GAN (WGAN) makes progress toward stable training of GANs, but sometimes can still generate only low-quality samples or fail to converge.
0
##### Improved Training of Wasserstein GANs
Generative Adversarial Networks (GANs) are powerful generative models, but suffer from training instability. The recently proposed Wasserstein GAN (WGAN) makes progress toward stable training of GANs, but sometimes can still generate only low-quality samples or fail to converge.
0
##### Improved Training of Wasserstein GANs
Generative Adversarial Networks (GANs) are powerful generative models, but suffer from training instability. The recently proposed Wasserstein GAN (WGAN) makes progress toward stable training of GANs, but sometimes can still generate only low-quality samples or fail to converge.
0
##### Hybrid Reward Architecture for Reinforcement Learning
One of the main challenges in reinforcement learning (RL) is generalisation. In typical deep RL methods this is achieved by approximating the optimal value function with a low-dimensional representation using a deep network.
0
##### Hybrid Reward Architecture for Reinforcement Learning
One of the main challenges in reinforcement learning (RL) is generalisation. In typical deep RL methods this is achieved by approximating the optimal value function with a low-dimensional representation using a deep network.
0