English
Related papers

Related papers: Rao-Blackwellizing the Straight-Through Gumbel-Sof…

200 papers

We present a latent variable model for classification that provides a novel probabilistic interpretation of neural network softmax classifiers. We derive a variational objective to train the model, analogous to the evidence lower bound…

Machine Learning · Computer Science 2024-01-10 Shehzaad Dhuliawala , Mrinmaya Sachan , Carl Allen

Softmax is widely used in neural networks for multiclass classification, gate structure and attention mechanisms. The statistical assumption that the input is normal distributed supports the gradient stability of Softmax. However, when used…

Computer Vision and Pattern Recognition · Computer Science 2021-08-17 Shulun Wang , Bin Liu , Feng Liu

We introduce local expectation gradients which is a general purpose stochastic variational inference algorithm for constructing stochastic gradients through sampling from the variational distribution. This algorithm divides the problem of…

Machine Learning · Statistics 2015-03-06 Michalis K. Titsias

The rapid increase in the parameters of deep learning models has led to significant costs, challenging computational efficiency and model interpretability. In this paper, we introduce a novel and straightforward neural network pruning…

Machine Learning · Computer Science 2023-11-23 Zhang Zhang , Ruyi Tao , Jiang Zhang

Optimization with noisy gradients has become ubiquitous in statistics and machine learning. Reparameterization gradients, or gradient estimates computed via the "reparameterization trick," represent a class of noisy gradients often used in…

Machine Learning · Statistics 2017-05-23 Andrew C. Miller , Nicholas J. Foti , Alexander D'Amour , Ryan P. Adams

Black Box Variational Inference is a promising framework in a succession of recent efforts to make Variational Inference more ``black box". However, in basic version it either fails to converge due to instability or requires some…

Machine Learning · Computer Science 2024-05-10 Dominic B. Dayta

We consider the problem of mean estimation assuming only finite variance. We study a new class of mean estimators constructed by integrating over random noise applied to a soft-truncated empirical mean estimator. For appropriate choices of…

Statistics Theory · Mathematics 2019-06-26 Matthew J. Holland

$k$-subset sampling is ubiquitous in machine learning, enabling regularization and interpretability through sparsity. The challenge lies in rendering $k$-subset sampling amenable to end-to-end learning. This has typically involved relaxing…

Machine Learning · Computer Science 2024-06-10 Kareem Ahmed , Zhe Zeng , Mathias Niepert , Guy Van den Broeck

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a powerful paradigm for post-training large reasoning models (LRMs) using policy-gradient methods such as GRPO. To stabilize training, these methods typically center…

Machine Learning · Computer Science 2026-02-19 Guanning Zeng , Zhaoyi Zhou , Daman Arora , Andrea Zanette

In light transport simulation, Markov chain Monte Carlo methods are particularly effective at exploring regions with complex lighting characteristics. However, estimator variance is a central concern across Monte Carlo methods in general.…

Computational Engineering, Finance, and Science · Computer Science 2026-05-12 Sascha Holl , Gurprit Singh , Hans-Peter Seidel

Many statistical estimators for high-dimensional linear regression are M-estimators, formed through minimizing a data-dependent square loss function plus a regularizer. This work considers a new class of estimators implicitly defined…

Statistics Theory · Mathematics 2022-02-15 Peng Zhao , Yun Yang , Qiao-Chu He

In computer science, there exist a large number of optimization problems defined on graphs, that is to find a best node state configuration or a network structure such that the designed objective function is optimized under some…

Machine Learning · Computer Science 2020-04-17 Yaoxin Li , Jing Liu , Guozheng Lin , Yueyuan Hou , Muyun Mou , Jiang Zhang

We introduce a new sufficient statistic for the population parameter vector by allowing for the sampling design to first be selected at random amongst a set of candidate sampling designs. In contrast to the traditional approach in survey…

Statistics Theory · Mathematics 2014-11-11 Kyle Vincent , Christopher S. Henry

In deep reinforcement learning, estimating the value function to evaluate the quality of states and actions is essential. The value function is often trained using the least squares method, which implicitly assumes a Gaussian error…

Machine Learning · Computer Science 2024-03-28 Motoki Omura , Takayuki Osa , Yusuke Mukuta , Tatsuya Harada

Under losses which are potentially heavy-tailed, we consider the task of minimizing sums of the loss mean and standard deviation, without trying to accurately estimate the variance. By modifying a technique for variance-free robust mean…

Machine Learning · Statistics 2024-02-12 Matthew J. Holland

A variance reduction technique in nonparametric smoothing is proposed: at each point of estimation, form a linear combination of a preliminary estimator evaluated at nearby points with the coefficients specified so that the asymptotic bias…

Statistics Theory · Mathematics 2007-08-22 Ming-Yen Cheng , Liang Peng , Jyh-Shyang Wu

In this manuscript the fixed-lag smoothing problem for conditionally linear Gaussian state-space models is investigated from a factor graph perspective. More specifically, after formulating Bayesian smoothing for an arbitrary state-space…

Computation · Statistics 2017-05-23 Giorgio M. Vitetta , Emilio Sirignano , Francesco Montorsi

Important applications such as mobile computing require reducing the computational costs of neural network inference. Ideally, applications would specify their preferred tradeoff between accuracy and speed, and the network would optimize…

Computer Vision and Pattern Recognition · Computer Science 2020-11-25 Charles Herrmann , Richard Strong Bowen , Ramin Zabih

Learning in models with discrete latent variables is challenging due to high variance gradient estimators. Generally, approaches have relied on control variates to reduce the variance of the REINFORCE estimator. Recent work (Jang et al.…

Machine Learning · Computer Science 2017-11-07 George Tucker , Andriy Mnih , Chris J. Maddison , Dieterich Lawson , Jascha Sohl-Dickstein

The Rao-Blackwell theorem is utilized to analyze and improve the scalability of inference in large probabilistic models that exhibit symmetries. A novel marginal density estimator is introduced and shown both analytically and empirically to…

Artificial Intelligence · Computer Science 2013-04-10 Mathias Niepert