English
Related papers

Related papers: Dynamic Oracles for Top-Down and In-Order Shift-Re…

200 papers

Gradient-based methods for optimisation of objectives in stochastic settings with unknown or intractable dynamics require estimators of derivatives. We derive an objective that, under automatic differentiation, produces low-variance…

Machine Learning · Computer Science 2019-09-25 Gregory Farquhar , Shimon Whiteson , Jakob Foerster

Recently, dynamic inference has emerged as a promising way to reduce the computational cost of deep convolutional neural network (CNN). In contrast to static methods (e.g. weight pruning), dynamic inference adaptively adjusts the inference…

Computer Vision and Pattern Recognition · Computer Science 2019-12-18 Zhihang Yuan , Bingzhe Wu , Zheng Liang , Shiwan Zhao , Weichen Bi , Guangyu Sun

Optimization in machine learning, both theoretical and applied, is presently dominated by first-order gradient methods such as stochastic gradient descent. Second-order optimization methods, that involve second derivatives and/or second…

Machine Learning · Computer Science 2021-03-08 Rohan Anil , Vineet Gupta , Tomer Koren , Kevin Regan , Yoram Singer

Recent works have shown that tackling offline reinforcement learning (RL) with a conditional policy produces promising results. The Decision Transformer (DT) combines the conditional policy approach and a transformer architecture, showing…

Machine Learning · Computer Science 2023-05-26 Taku Yamagata , Ahmed Khalil , Raul Santos-Rodriguez

In Transformer-based neural machine translation (NMT), the positional encoding mechanism helps the self-attention networks to learn the source representation with order dependency, which makes the Transformer-based NMT achieve…

Computation and Language · Computer Science 2020-04-09 Kehai Chen , Rui Wang , Masao Utiyama , Eiichiro Sumita

Higher-order tensor methods were recently proposed for minimizing smooth convex and nonconvex functions. Higher-order algorithms accelerate the convergence of the classical first-order methods thanks to the higher-order derivatives used in…

Optimization and Control · Mathematics 2024-01-11 Ion Necoara

This article provides a rigorous analysis of convergence and stability of Episodic Upside-Down Reinforcement Learning, Goal-Conditioned Supervised Learning and Online Decision Transformers. These algorithms performed competitively across…

Recent focus on robustness to adversarial attacks for deep neural networks produced a large variety of algorithms for training robust models. Most of the effective algorithms involve solving the min-max optimization problem for training…

Machine Learning · Computer Science 2021-03-03 Yasaman Esfandiari , Aditya Balu , Keivan Ebrahimi , Umesh Vaidya , Nicola Elia , Soumik Sarkar

Detecting critical transitions in complex, noisy time-series data is a fundamental challenge across science and engineering. Such transitions may be anticipated by the emergence of a low-dimensional order parameter, whose signature is often…

Machine Learning · Computer Science 2025-12-16 Wenqi Fang , Ye Li

In this paper, we propose an algorithm for the construction of low-rank approximations of the inverse of an operator given in low-rank tensor format. The construction relies on an updated greedy algorithm for the minimization of a suitable…

Numerical Analysis · Mathematics 2017-05-11 Loic Giraldi , Anthony Nouy , Gregory Legrain

Offline Reinforcement learning is commonly used for sequential decision-making in domains such as healthcare and education, where the rewards are known and the transition dynamics $T$ must be estimated on the basis of batch data. A key…

Machine Learning · Computer Science 2023-08-10 Leo Benac , Sonali Parbhoo , Finale Doshi-Velez

This paper presents a linear dynamical operator described in terms of a rational transfer function, endowed with a well-defined and efficient back-propagation behavior for automatic derivatives computation. The operator enables end-to-end…

Machine Learning · Computer Science 2021-04-21 Dario Piga , Marco Forgione , Manas Mejari

Transformers have transformed modern machine learning, driving breakthroughs in computer vision, natural language processing, and robotics. At the core of their success lies the attention mechanism, which enables the modeling of global…

Computer Vision and Pattern Recognition · Computer Science 2025-10-07 Hemanth Saratchandran , Simon Lucey

This work studies constrained stochastic optimization problems where the objective and constraint functions are convex and expressed as compositions of stochastic functions. The problem arises in the context of fair classification, fair…

Machine Learning · Computer Science 2022-09-13 Srujan Teja Thomdapu , Harshvardhan , Ketan Rajawat

We present a new dynamic partial-order reduction method for stateless model checking of concurrent programs. A common approach for exploring program behaviors relies on enumerating the traces of the program, without storing the visited…

Programming Languages · Computer Science 2019-01-28 Marek Chalupa , Krishnendu Chatterjee , Andreas Pavlogiannis , Nishant Sinha , Kapil Vaidya

In order to achieve deep natural language understanding, syntactic constituent parsing is a vital step, highly demanded by many artificial intelligence systems to process both text and speech. One of the most recent proposals is the use of…

Computation and Language · Computer Science 2022-12-26 Daniel Fernández-González , Carlos Gómez-Rodríguez

Recurrent neural networks (RNNs) achieve cutting-edge performance on a variety of problems. However, due to their high computational and memory demands, deploying RNNs on resource constrained mobile devices is a challenging task. To…

Machine Learning · Computer Science 2018-06-12 Jie Zhang , Xiaolong Wang , Dawei Li , Yalin Wang

Long-context multiple-choice question answering tasks require robust reasoning over extensive text sources. Since most of the pre-trained transformer models are restricted to processing only a few hundred words at a time, successful…

Information Retrieval · Computer Science 2025-01-28 Manish Singh , Manish Shrivastava

Motivated by emerging applications in machine learning, we consider an optimization problem in a general form where the gradient of the objective function is available through a biased stochastic oracle. We assume a bias-control parameter…

Optimization and Control · Mathematics 2026-02-10 Yin Liu , Sam Davanloo Tajbakhsh

This work constructs and analyzes new efficient high-order two-derivative diagonally implicit Runge--Kutta (TDDIRK) schemes with optimized phase errors. Specifically, we present a convergence result for TDDIRK methods and investigate their…

Numerical Analysis · Mathematics 2025-12-18 Julius Ehigie , Vu Thai Luan