English
Related papers

Related papers: Beyond ReinMax: Low-Variance Gradient Estimators f…

200 papers

Deep latent variable models have achieved significant empirical successes in model-based reinforcement learning (RL) due to their expressiveness in modeling complex transition dynamics. On the other hand, it remains unclear theoretically…

Machine Learning · Computer Science 2023-03-08 Tongzheng Ren , Chenjun Xiao , Tianjun Zhang , Na Li , Zhaoran Wang , Sujay Sanghavi , Dale Schuurmans , Bo Dai

One of the major challenges in multivariate analysis is the estimation of population covariance matrix from sample covariance matrix (SCM). Most recent covariance matrix estimators use either shrinkage transformations or asymptotic results…

Methodology · Statistics 2019-12-10 Samruddhi Deshmukh , Amartansh Dubey

We introduce a family of pairwise stochastic gradient estimators for gradients of expectations, which are related to the log-derivative trick, but involve pairwise interactions between samples. The simplest example of our new estimator,…

Machine Learning · Computer Science 2022-04-21 Christian J. Walder , Paul Roussel , Richard Nock , Cheng Soon Ong , Masashi Sugiyama

Statistical inference methods are fundamentally important in machine learning. Most state-of-the-art inference algorithms are variants of Markov chain Monte Carlo (MCMC) or variational inference (VI). However, both methods struggle with…

Machine Learning · Computer Science 2019-10-17 Yichuan Zhang , José Miguel Hernández-Lobato

In this work we address the problem of convex optimization in a multi-agent setting where the objective is to minimize the mean of local cost functions whose derivatives are not available (e.g. black-box models). Moreover agents can only…

Optimization and Control · Mathematics 2023-06-14 Alessio Maritan , Luca Schenato

Low-rank modeling has a lot of important applications in machine learning, computer vision and social network analysis. While the matrix rank is often approximated by the convex nuclear norm, the use of nonconvex low-rank regularizers has…

Numerical Analysis · Computer Science 2016-05-02 Quanming Yao , James T. Kwok , Wenliang Zhong

Trajectory forecasting is crucial for video surveillance analytics, as it enables the anticipation of future movements for a set of agents, e.g. basketball players engaged in intricate interactions with long-term intentions. Deep generative…

Computer Vision and Pattern Recognition · Computer Science 2024-08-30 Riccardo Benaglia , Angelo Porrello , Pietro Buzzega , Simone Calderara , Rita Cucchiara

Variational autoencoders employ an amortized inference model to approximate the posterior of latent variables. However, such amortized variational inference faces two challenges: (1) the limited posterior expressiveness of fully-factorized…

Machine Learning · Computer Science 2022-12-01 Yookoon Park , Chris Dongjoo Kim , Gunhee Kim

Many optimization problems require hyperparameters, i.e., parameters that must be pre-specified in advance, such as regularization parameters and parametric regularizers in variational regularization methods for inverse problems, and…

Optimization and Control · Mathematics 2025-10-09 Matthias J. Ehrhardt , Silvia Gazzola , Sebastian J. Scott

In this paper we introduce new estimators of the coefficient functions in the varying coefficient regression model. The proposed estimators are obtained by projecting the vector of the full-dimensional kernel-weighted local polynomial…

Statistics Theory · Mathematics 2012-03-05 Young K. Lee , Enno Mammen , Byeong U. Park

Recent advances in reinforcement learning (RL) have substantially improved the training of large-scale language models, leading to significant gains in generation quality and reasoning ability. However, most existing research focuses on…

Machine Learning · Computer Science 2026-01-13 Di Zhang , Xun Wu , Shaohan Huang , Lingjie Jiang , Yaru Hao , Li Dong , Zewen Chi , Zhifang Sui , Furu Wei

Variational Autoencoders are powerful models for unsupervised learning. However deep models with several layers of dependent stochastic variables are difficult to train which limits the improvements obtained using these highly expressive…

Machine Learning · Statistics 2016-05-30 Casper Kaae Sønderby , Tapani Raiko , Lars Maaløe , Søren Kaae Sønderby , Ole Winther

Value Iteration Networks (VINs) have emerged as a popular method to incorporate planning algorithms within deep reinforcement learning, enabling performance improvements on tasks requiring long-range reasoning and understanding of…

Machine Learning · Computer Science 2020-12-08 Andreea Deac , Petar Veličković , Ognjen Milinković , Pierre-Luc Bacon , Jian Tang , Mladen Nikolić

Variational Autoencoders (VAEs) are a powerful framework for learning latent representations of reduced dimensionality, while Neural ODEs excel in learning transient system dynamics. This work combines the strengths of both to generate fast…

Machine Learning · Computer Science 2025-02-27 Julius Aka , Johannes Brunnemann , Jörg Eiden , Arne Speerforck , Lars Mikelsons

Fine-tuning pre-trained generative models with Reinforcement Learning (RL) has emerged as an effective approach for aligning outputs more closely with nuanced human preferences. In this paper, we investigate the application of Group…

Computer Vision and Pattern Recognition · Computer Science 2025-07-01 Matteo Gallici , Haitz Sáez de Ocáriz Borde

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

A new method for learning variational autoencoders (VAEs) is developed, based on Stein variational gradient descent. A key advantage of this approach is that one need not make parametric assumptions about the form of the encoder…

Machine Learning · Computer Science 2017-11-20 Yunchen Pu , Zhe Gan , Ricardo Henao , Chunyuan Li , Shaobo Han , Lawrence Carin

We present Re-weighted Gradient Descent (RGD), a novel optimization technique that improves the performance of deep neural networks through dynamic sample re-weighting. Leveraging insights from distributionally robust optimization (DRO)…

Machine Learning · Computer Science 2024-10-15 Ramnath Kumar , Kushal Majmundar , Dheeraj Nagaraj , Arun Sai Suggala

Bilevel optimization is a powerful tool for many machine learning problems, such as hyperparameter optimization and meta-learning. Estimating hypergradients (also known as implicit gradients) is crucial for developing gradient-based methods…

Optimization and Control · Mathematics 2025-05-06 Youran Dong , Junfeng Yang , Wei Yao , Jin Zhang

In this work, we analyze two of the most fundamental algorithms in geodesically convex optimization: Riemannian gradient descent and (possibly inexact) Riemannian proximal point. We quantify their rates of convergence and produce different…

Optimization and Control · Mathematics 2024-03-18 David Martínez-Rubio , Christophe Roux , Sebastian Pokutta