Search Results for author:
Found 17 papers, 11 papers with code
Coevolution of Resource and Strategies in Common-Pool Resource Dilemmas: A Coupled Human-Environmental System Model
The users' strategies evolve according to different processes that capture effects of payoff, resource, and noise.
Impact of resource availability and conformity effect on sustainability of common-pool resources
However, there is still a lack of a novel and comprehensive framework for modelling extraction of common-pool resources and cooperation of human agents that can account for different factors that shape the system behavior and outcomes.
DPOK: Reinforcement Learning for Fine-tuning Text-to-Image Diffusion Models
We focus on diffusion models, defining the fine-tuning task as an RL problem, and updating the pre-trained text-to-image diffusion models using policy gradient to maximize the feedback-trained reward.
Domain Generalization via Nuclear Norm Regularization
In this paper, we propose a simple and effective regularization method based on the nuclear norm of the learned features for domain generalization.
Optimizing DDPM Sampling with Shortcut Fine-Tuning
In this study, we propose Shortcut Fine-Tuning (SFT), a new approach for addressing the challenge of fast sampling of pretrained Denoising Diffusion Probabilistic Models (DDPMs).
Score-based Generative Modeling Secretly Minimizes the Wasserstein Distance
Specifically, we prove that the Wasserstein distance is upper bounded by the square root of the objective function up to multiplicative constants and a fixed constant offset.
POEM: Out-of-Distribution Detection with Posterior Sampling
In this work, we propose a novel posterior sampling-based outlier mining framework, POEM, which facilitates efficient use of outlier data and promotes learning a compact decision boundary between ID and OOD data for improved detection.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
Towards Unknown-aware Deep Q-Learning
Furthermore, we provide theoretical guarantees that our method can improve OOD uncertainty estimation while ensuring the convergence performance of the in-distribution environment.
Real Negatives Matter: Continuous Training with Real Negatives for Delayed Feedback Modeling
If conversion happens outside the waiting window, this sample will be duplicated and ingested into the training pipeline with a positive label.
Model-based Reinforcement Learning for Continuous Control with Posterior Sampling
In this paper, we study model-based posterior sampling for reinforcement learning (PSRL) in continuous state-action spaces theoretically and empirically.
Efficient Exploration for Model-based Reinforcement Learning with Continuous States and Actions
Our bound can be extended to nonlinear cases as well: using linear kernels on the feature representation $\phi$, the Bayesian regret bound becomes $\tilde{O}(H^{3/2}d_{\phi}\sqrt{T})$, where $d_\phi$ is the dimension of the representation space.
Search-based User Interest Modeling with Lifelong Sequential Behavior Data for Click-Through Rate Prediction
Serving the main traffic in our real system now, SIM models user behavior data with maximum length reaching up to 54000, pushing SOTA to 54x.
A hyperbolic Embedding Model for Directed Networks
Here, we discuss how to multiplex node information as an embedding foundation through identifying the bipartite structure of directed networks; and we proposed the generally mapping framework which hybrids the topological structure of complex networks, directed links and the hidden metrics space.
Physics and Society
Efficient Model-Free Reinforcement Learning Using Gaussian Process
Efficient Reinforcement Learning usually takes advantage of demonstration or good exploration strategy.
Deep Interest Evolution Network for Click-Through Rate Prediction
Easy-to-use, Modular and Extendible package of deep-learning based CTR models. DeepFM, DeepInterestNetwork(DIN), DeepInterestEvolutionNetwork(DIEN), DeepCrossNetwork(DCN), AttentionalFactorizationMachine(AFM), Neural Factorization Machine(NFM), AutoInt
Ranked #1 on
Click-Through Rate Prediction
on Amazon Dataset
Rocket Launching: A Universal and Efficient Framework for Training Well-performing Light Net
Models applied on real time response task, like click-through rate (CTR) prediction model, require high accuracy and rigorous response time.
Deep Interest Network for Click-Through Rate Prediction
In this way, user features are compressed into a fixed-length representation vector, in regardless of what candidate ads are.
Ranked #1 on
Click-Through Rate Prediction
on Amazon
