English
Related papers

Related papers: Deep Reinforcement Learning via L-BFGS Optimizatio…

200 papers

First-order methods like stochastic gradient descent(SGD) are recently the popular optimization method to train deep neural networks (DNNs), but second-order methods are scarcely used because of the overpriced computing cost in getting the…

Machine Learning · Computer Science 2021-04-01 Jingcheng Zhou , Wei Wei , Zhiming Zheng

The question of how to incorporate curvature information in stochastic approximation methods is challenging. The direct application of classical quasi- Newton updating techniques for deterministic optimization leads to noisy curvature…

Optimization and Control · Mathematics 2015-02-19 R. H. Byrd , S. L. Hansen , J. Nocedal , Y. Singer

The main focus in this paper is exact linesearch methods for minimizing a quadratic function whose Hessian is positive definite. We give a class of limited-memory quasi-Newton Hessian approximations which generate search directions parallel…

Optimization and Control · Mathematics 2023-05-04 David Ek , Anders Forsgren

Stochastic optimization methods have become a class of popular optimization tools in machine learning. Especially, stochastic gradient descent (SGD) has been widely used for machine learning problems such as training neural networks due to…

Optimization and Control · Mathematics 2021-02-26 Qingsong Zhang , Feihu Huang , Cheng Deng , Heng Huang

Reinforcement learning (RL) with sparse and deceptive rewards is challenging because non-zero rewards are rarely obtained. Hence, the gradient calculated by the agent can be stochastic and without valid information. Recent studies that…

Machine Learning · Computer Science 2024-02-08 Guojian Wang , Faguo Wu , Xiao Zhang , Jianxiang Liu

In recent years significant progress has been made in dealing with challenging problems using reinforcement learning.Despite its great success, reinforcement learning still faces challenge in continuous control tasks. Conventional methods…

Machine Learning · Computer Science 2020-02-04 Longxiang Shi , Shijian Li , Longbing Cao , Long Yang , Gang Zheng , Gang Pan

Two-time-scale optimization is a framework introduced in Zeng et al. (2024) that abstracts a range of policy evaluation and policy optimization problems in reinforcement learning (RL). Akin to bi-level optimization under a particular type…

Optimization and Control · Mathematics 2026-01-21 Sihan Zeng , Thinh T. Doan

Fast gradient-based optimization algorithms have become increasingly essential for the computationally efficient training of machine learning models. One technique is to multiply the gradient by a preconditioner matrix to produce a step,…

Machine Learning · Computer Science 2023-09-12 Isaac Liao , Rumen R. Dangovski , Jakob N. Foerster , Marin Soljačić

Second-order methods have the capability of accelerating optimization by using much richer curvature information than first-order methods. However, most are impractical for deep learning, where the number of training parameters is huge. In…

Machine Learning · Computer Science 2022-02-22 Yi Ren , Achraf Bahamou , Donald Goldfarb

Branch-and-bound is a systematic enumerative method for combinatorial optimization, where the performance highly relies on the variable selection strategy. State-of-the-art handcrafted heuristic strategies suffer from relatively slow…

Machine Learning · Computer Science 2022-06-15 Tianyu Zhang , Amin Banitalebi-Dehkordi , Yong Zhang

Modern machine learning is trained by stochastic gradient descent (SGD), whose performance critically depends on how the learning rate (LR) is adjusted and decreased over time. Yet existing LR regimes may be intricate, or need to tune one…

Machine Learning · Computer Science 2025-08-20 Zhuang Yang

We propose a new class of deep reinforcement learning (RL) algorithms that model latent representations in hyperbolic space. Sequential decision-making requires reasoning about the possible future consequences of current behavior.…

Machine Learning · Computer Science 2022-10-05 Edoardo Cetin , Benjamin Chamberlain , Michael Bronstein , Jonathan J Hunt

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

Mean Field Games (MFGs) have been introduced to efficiently approximate games with very large populations of strategic agents. Recently, the question of learning equilibria in MFGs has gained momentum, particularly using model-free…

We investigate quasi-Newton methods for minimizing a strictly convex quadratic function which is subject to errors in the evaluation of the gradients. The methods all give identical behavior in exact arithmetic, generating minimizers of…

Optimization and Control · Mathematics 2025-02-26 Shen Peng , Gianpiero Canessa , David Ek , Anders Forsgren

A displacement aggregation strategy is proposed for the curvature pairs stored in a limited-memory BFGS (a.k.a. L-BFGS) method such that the resulting (inverse) Hessian approximations are equal to those that would be derived from a…

Optimization and Control · Mathematics 2020-08-27 Albert S. Berahas , Frank E. Curtis , Baoyu Zhou

The field of quickest change detection (QCD) concerns design and analysis of algorithms to estimate in real time the time at which an important event takes place, and identify properties of the post-change behavior. It is shown in this…

Optimization and Control · Mathematics 2024-09-16 Austin Cooper , Sean Meyn

Despite overparameterization, deep networks trained via supervised learning are easy to optimize and exhibit excellent generalization. One hypothesis to explain this is that overparameterized deep networks enjoy the benefits of implicit…

Machine Learning · Computer Science 2021-12-10 Aviral Kumar , Rishabh Agarwal , Tengyu Ma , Aaron Courville , George Tucker , Sergey Levine

We present an efficient quasi-Newton orbital solver optimized to reduce the number of gradient (Fock matrix) evaluations. The solver optimizes orthogonal orbitals by sequences of unitary rotations generated by the (preconditioned)…

Chemical Physics · Physics 2023-12-20 Samuel A. Slattery , Kshitijkumar Surjuse , Edward F. Valeev

L-BFGS is the state-of-the-art optimization method for many large scale inverse problems. It has a small memory footprint and achieves superlinear convergence. The method approximates Hessian based on an initial approximation and an update…

Numerical Analysis · Mathematics 2021-03-19 Hari Om Aggrawal , Jan Modersitzki