Search Results for author:
Found 22 papers, 4 papers with code
Post-training Quantization with Multiple Points: Mixed Precision without Mixed Precision
We propose multipoint quantization, a quantization method that approximates a full-precision weight vector using a linear combination of multiple vectors of low-bit numbers; this is in contrast to typical quantization methods that approximate each weight using a single low precision number.
Doubly Robust Bias Reduction in Infinite Horizon Off-Policy Estimation
Our method is doubly robust in that the bias vanishes when either the density ratio or the value function estimation is perfect.
Neural Phrase-to-Phrase Machine Translation
We also design an efficient dynamic programming algorithm to decode segments that allows the model to be trained faster than the existing neural phrase-based machine translation method by Huang et al. (2018).
Breaking the Curse of Horizon: Infinite-Horizon Off-Policy Estimation
We consider the off-policy estimation problem of estimating the expected reward of a target policy using samples collected by a different behavior policy.
Action-dependent Control Variates for Policy Optimization via Stein Identity
Policy gradient methods have achieved remarkable successes in solving challenging reinforcement learning problems.
On the Discrimination-Generalization Tradeoff in GANs
When evaluated with neural distance, our bounds show that generalization is guaranteed as long as the discriminator set is small enough, regardless of the size of the generator or hypothesis set.
Action-depedent Control Variates for Policy Optimization via Stein's Identity
Policy gradient methods have achieved remarkable successes in solving challenging reinforcement learning problems.
Towards Neural Phrase-based Machine Translation
In this paper, we present Neural Phrase-based Machine Translation (NPMT).
Ranked #7 on
Machine Translation
on IWSLT2015 English-German
Provably Optimal Algorithms for Generalized Linear Contextual Bandits
Contextual bandits are widely used in Internet services from news recommendation to advertising, and to Web search.
Stochastic Variance Reduction Methods for Policy Evaluation
Policy evaluation is a crucial step in many reinforcement-learning procedures, which estimates a value function that predicts states' long-term value under a given policy.
Sequence Modeling via Segmentations
The probability of a segmented sequence is calculated as the product of the probabilities of all its segments, where each segment is modeled using existing tools such as recurrent neural networks.
Neuro-Symbolic Program Synthesis
While achieving impressive results, these approaches have a number of important limitations: (a) they are computationally expensive and hard to train, (b) a model has to be trained for each task (program) separately, and (c) it is hard to interpret or verify the correctness of the learnt mapping (as it is defined by a neural network).
Exact Exponent in Optimal Rates for Crowdsourcing
In many machine learning applications, crowdsourcing has become the primary means for label collection.
Regularized Minimax Conditional Entropy for Crowdsourcing
There is a rapidly increasing interest in crowdsourcing for data labeling.
Approval Voting and Incentives in Crowdsourcing
The growing need for labeled training data has made crowdsourcing an important part of machine learning.
On the Impossibility of Convex Inference in Human Computation
Human computation or crowdsourcing involves joint inference of the ground-truth-answers and the worker-abilities by optimizing an objective function, for instance, by maximizing the data likelihood based on an assumed underlying model.
Double or Nothing: Multiplicative Incentive Mechanisms for Crowdsourcing
To address this fundamental challenge in crowdsourcing, we propose a simple payment mechanism to incentivize workers to answer only the questions that they are sure of and skip the rest.
Spectral Methods meet EM: A Provably Optimal Algorithm for Crowdsourcing
Crowdsourcing is a popular paradigm for effectively collecting labels at low cost.
Statistical Decision Making for Optimal Budget Allocation in Crowd Labeling
In crowd labeling, a large amount of unlabeled data instances are outsourced to a crowd of workers.
Minimax Optimal Convergence Rates for Estimating Ground Truth from Crowdsourced Labels
Crowdsourcing has become a primary means for label collection in many real-world machine learning applications.
Error Rate Bounds in Crowdsourcing Models
We show that the oracle Maximum A Posterior (MAP) rule approximately optimizes our upper bound on the mean error rate for any hyperplane binary labeling rule, and propose a simple data-driven weighted majority voting (WMV) rule (called one-step WMV) that attempts to approximate the oracle MAP and has a provable theoretical guarantee on the error rate.
Learning from the Wisdom of Crowds by Minimax Entropy
We propose a minimax entropy principle to improve the quality of these labels.
