English
Related papers

Related papers: Amortized Bethe Free Energy Minimization for Learn…

200 papers

We address the problem of learning the parameters in graphical models when inference is intractable. A common strategy in this case is to replace the partition function with its Bethe approximation. We show that there exists a regime of…

Machine Learning · Computer Science 2012-02-20 Uri Heinemann , Amir Globerson

We propose a simple yet effective neural network-based framework for global illumination rendering. Recently, rendering techniques that learn neural radiance caches by minimizing the difference (i.e., residual) between the left and right…

Computer Vision and Pattern Recognition · Computer Science 2024-10-15 In-Young Cho , Jaewoong Cho

Model-based reinforcement learning (RL) is considered to be a promising approach to reduce the sample complexity that hinders model-free RL. However, the theoretical understanding of such methods has been rather limited. This paper…

Machine Learning · Computer Science 2021-02-16 Yuping Luo , Huazhe Xu , Yuanzhi Li , Yuandong Tian , Trevor Darrell , Tengyu Ma

Model-free reinforcement learning is known to be memory and computation efficient and more amendable to large scale problems. In this paper, two model-free algorithms are introduced for learning infinite-horizon average-reward Markov…

Machine Learning · Computer Science 2020-02-26 Chen-Yu Wei , Mehdi Jafarnia-Jahromi , Haipeng Luo , Hiteshi Sharma , Rahul Jain

Training deep generative models like Variational Autoencoders (VAEs) requires propagating gradients through stochastic latent variables, which introduces estimation variance that can slow convergence and degrade performance. In this paper,…

Machine Learning · Computer Science 2026-02-27 Zilei Shao , Anji Liu , Guy Van den Broeck

Many problems in machine learning are naturally expressed in the language of undirected graphical models. Here, we propose black-box learning and inference algorithms for undirected models that optimize a variational approximation to the…

Machine Learning · Computer Science 2017-11-20 Volodymyr Kuleshov , Stefano Ermon

Derivative-Free Optimization (DFO) involves methods that rely solely on evaluations of the objective function. One of the earliest strategies for designing DFO methods is to adapt first-order methods by replacing gradients with…

Optimization and Control · Mathematics 2025-02-12 Timothé Taminiau , Estelle Massart , Geovani Nunes Grapiglia

This paper focuses on training implicit models of infinite layers. Specifically, previous works employ implicit differentiation and solve the exact gradient for the backward propagation. However, is it necessary to compute such an exact but…

Machine Learning · Computer Science 2022-01-13 Zhengyang Geng , Xin-Yu Zhang , Shaojie Bai , Yisen Wang , Zhouchen Lin

We propose a neural network-based algorithm for solving forward and inverse problems for partial differential equations in unsupervised fashion. The solution is approximated by a deep neural network which is the minimizer of a cost…

Machine Learning · Computer Science 2019-04-12 Leah Bar , Nir Sochen

We propose an algorithm for inexpensive gradient-based hyperparameter optimization that combines the implicit function theorem (IFT) with efficient inverse Hessian approximations. We present results about the relationship between the IFT…

Machine Learning · Computer Science 2019-11-11 Jonathan Lorraine , Paul Vicol , David Duvenaud

Inverse Reinforcement Learning addresses the problem of inferring an expert's reward function from demonstrations. However, in many applications, we not only have access to the expert's near-optimal behavior, but we also observe part of her…

Machine Learning · Computer Science 2021-09-03 Giorgia Ramponi , Gianluca Drappo , Marcello Restelli

A crucial problem in reinforcement learning is learning the optimal policy. We study this in tabular infinite-horizon discounted Markov decision processes under the online setting. The existing algorithms either fail to achieve regret…

Machine Learning · Computer Science 2023-12-13 Xiang Ji , Gen Li

Implicit representations such as Neural Radiance Fields (NeRF) have been shown to be very effective at novel view synthesis. However, these models typically require manual and careful human data collection for training. In this paper, we…

Computer Vision and Pattern Recognition · Computer Science 2023-12-25 Pierre Marza , Laetitia Matignon , Olivier Simonin , Dhruv Batra , Christian Wolf , Devendra Singh Chaplot

Bayesian inference for models with intractable likelihoods, such as Markov random fields, poses a fundamental computational challenge due to the tradeoff between inferential accuracy and computational cost. Various MCMC methods have been…

Methodology · Statistics 2026-04-01 Laura Bazahica , Alejandra Avalos-Pacheco , Matthew Moores , Lassi Roininen

Randomly initialized first-order optimization algorithms are the method of choice for solving many high-dimensional nonconvex problems in machine learning, yet general theoretical guarantees cannot rule out convergence to critical points of…

Optimization and Control · Mathematics 2018-09-28 Dar Gilboa , Sam Buchanan , John Wright

The paper considers distributed gradient flow (DGF) for multi-agent nonconvex optimization. DGF is a continuous-time approximation of distributed gradient descent that is often easier to study than its discrete-time counterpart. The paper…

Optimization and Control · Mathematics 2020-08-13 Brian Swenson , Ryan Murray , H. Vincent Poor , Soummya Kar

This paper presents an entirely unsupervised interest point training framework by jointly learning detector and descriptor, which takes an image as input and outputs a probability and a description for every image point. The objective of…

Computer Vision and Pattern Recognition · Computer Science 2019-07-29 Pei Yan , Yihua Tan , Yuan Xiao , Yuan Tai , Cai Wen

In the context of inference with expectation constraints, we propose an approach based on the "loopy belief propagation" algorithm LBP, as a surrogate to an exact Markov Random Field MRF modelling. A prior information composed of…

Machine Learning · Computer Science 2015-05-13 Cyril Furtlehner , Jean-Marc Lasgouttes , Anne Auger

Graphical models are a rich language for describing high-dimensional distributions in terms of their dependence structure. While there are algorithms with provable guarantees for learning undirected graphical models in a variety of…

Machine Learning · Computer Science 2018-11-07 Guy Bresler , Frederic Koehler , Ankur Moitra , Elchanan Mossel

Learning energy-based models (EBMs) is known to be difficult especially on discrete data where gradient-based learning strategies cannot be applied directly. Although ratio matching is a sound method to learn discrete EBMs, it suffers from…

Machine Learning · Computer Science 2023-02-28 Meng Liu , Haoran Liu , Shuiwang Ji