English
Related papers

Related papers: Training Conditional Random Fields with Natural Gr…

200 papers

Convolutional neural networks are widely used in imaging and image recognition. Learning such networks from training data leads to the minimization of a non-convex function. This makes the analysis of standard optimization methods such as…

Optimization and Control · Mathematics 2026-01-14 Jona-Maria Diederen , Holger Rauhut , Ulrich Terstiege

We consider the problem of minimizing the sum of two convex functions: one is smooth and given by a gradient oracle, and the other is separable over blocks of coordinates and has a simple known structure over each block. We develop an…

Optimization and Control · Mathematics 2014-07-07 Qihang Lin , Zhaosong Lu , Lin Xiao

Reparameterization (RP) and likelihood ratio (LR) gradient estimators are used throughout machine and reinforcement learning; however, they are usually explained as simple mathematical tricks without providing any insight into their nature.…

Machine Learning · Computer Science 2019-10-16 Paavo Parmas , Masashi Sugiyama

We study the segmental recurrent neural network for end-to-end acoustic modelling. This model connects the segmental conditional random field (CRF) with a recurrent neural network (RNN) used for feature extraction. Compared to most previous…

Computation and Language · Computer Science 2016-06-21 Liang Lu , Lingpeng Kong , Chris Dyer , Noah A. Smith , Steve Renals

Motivated by penalized likelihood maximization in complex models, we study optimization problems where neither the function to optimize nor its gradient have an explicit expression, but its gradient can be approximated by a Monte Carlo…

Computation · Statistics 2017-09-28 Gersende Fort , Edouard Ollier , Adeline Samson

Gradient descent (GD) methods for the training of artificial neural networks (ANNs) belong nowadays to the most heavily employed computational schemes in the digital world. Despite the compelling success of such methods, it remains an open…

Optimization and Control · Mathematics 2025-09-01 Shokhrukh Ibragimov , Arnulf Jentzen , Adrian Riekert

In modern radar systems, precise target localization using azimuth and velocity estimation is paramount. Traditional unbiased estimation methods have utilized gradient descent algorithms to reach the theoretical limits of the Cramer Rao…

Signal Processing · Electrical Eng. & Systems 2024-04-24 Shyam Venkatasubramanian , Sandeep Gogineni , Bosung Kang , Muralidhar Rangaswamy

Risk-sensitive reinforcement learning (RL) is crucial for maintaining reliable performance in high-stakes applications. While traditional RL methods aim to learn a point estimate of the random cumulative cost, distributional RL (DRL) seeks…

Machine Learning · Computer Science 2025-02-03 Minheng Xiao , Xian Yu , Lei Ying

A recent line of research has shown that gradient-based algorithms with random initialization can converge to the global minima of the training loss for over-parameterized (i.e., sufficiently wide) deep neural networks. However, the…

Machine Learning · Computer Science 2019-06-12 Difan Zou , Quanquan Gu

We propose a novel framework to solve risk-sensitive reinforcement learning (RL) problems where the agent optimises time-consistent dynamic spectral risk measures. Based on the notion of conditional elicitability, our methodology constructs…

Machine Learning · Computer Science 2023-05-02 Anthony Coache , Sebastian Jaimungal , Álvaro Cartea

In the paper, we design a novel Bregman gradient policy optimization framework for reinforcement learning based on Bregman divergences and momentum techniques. Specifically, we propose a Bregman gradient policy optimization (BGPO) algorithm…

Machine Learning · Computer Science 2022-03-17 Feihu Huang , Shangqian Gao , Heng Huang

Neural networks trained with standard objectives exhibit behaviors characteristic of probabilistic inference: soft clustering, prototype specialization, and Bayesian uncertainty tracking. These phenomena appear across architectures -- in…

Machine Learning · Computer Science 2026-01-01 Alan Oursland

Although well-established in general reinforcement learning (RL), value-based methods are rarely explored in constrained RL (CRL) for their incapability of finding policies that can randomize among multiple actions. To apply value-based…

Machine Learning · Computer Science 2022-06-28 Tianchi Cai , Wenpeng Zhang , Lihong Gu , Xiaodong Zeng , Jinjie Gu

Natural gradient descent has a remarkable property that in the small learning rate limit, it displays an invariance with respect to network reparameterizations, leading to robust training behavior even for highly covariant network…

Machine Learning · Statistics 2023-12-11 Christian Goodbrake

In this paper, we propose a simple, fast and easy to implement algorithm LOSSGRAD (locally optimal step-size in gradient descent), which automatically modifies the step-size in gradient descent during neural networks training. Given a…

Machine Learning · Computer Science 2019-11-26 Bartosz Wójcik , Łukasz Maziarka , Jacek Tabor

Natural gradients have been widely used in optimization of loss functionals over probability space, with important examples such as Fisher-Rao gradient descent for Kullback-Leibler divergence, Wasserstein gradient descent for…

Numerical Analysis · Mathematics 2020-06-30 Lexing Ying

In a variety of problems originating in supervised, unsupervised, and reinforcement learning, the loss function is defined by an expectation over a collection of random variables, which might be part of a probabilistic model or the external…

Machine Learning · Computer Science 2016-01-06 John Schulman , Nicolas Heess , Theophane Weber , Pieter Abbeel

Continual learning is an emerging paradigm in machine learning, wherein a model is exposed in an online fashion to data from multiple different distributions (i.e. environments), and is expected to adapt to the distribution change.…

Machine Learning · Computer Science 2022-03-29 Binghui Peng , Andrej Risteski

With advances in deep learning, exponential data growth and increasing model complexity, developing efficient optimization methods are attracting much research attention. Several implementations favor the use of Conjugate Gradient (CG) and…

Machine Learning · Computer Science 2020-03-02 Buse Melis Ozyildirim , Mariam Kiran

We study randomized variants of two classical algorithms: coordinate descent for systems of linear equations and iterated projections for systems of linear inequalities. Expanding on a recent randomized iterated projection algorithm of…

Optimization and Control · Mathematics 2008-06-19 D. Leventhal , A. S. Lewis