English
Related papers

Related papers: Learning the Step-size Policy for the Limited-Memo…

200 papers

We propose a new per-layer adaptive step-size procedure for stochastic first-order optimization methods for minimizing empirical loss functions in deep learning, eliminating the need for the user to tune the learning rate (LR). The proposed…

Machine Learning · Computer Science 2023-07-07 Achraf Bahamou , Donald Goldfarb

In this paper we study stochastic quasi-Newton methods for nonconvex stochastic optimization, where we assume that noisy information about the gradients of the objective function is available via a stochastic first-order oracle (SFO). We…

Optimization and Control · Mathematics 2017-05-23 Xiao Wang , Shiqian Ma , Donald Goldfarb , Wei Liu

Numerical optimization is an important tool in the field of computational physics in general and in nano-optics in specific. It has attracted attention with the increase in complexity of structures that can be realized with nowadays…

Update formulas for the Hessian approximations in quasi-Newton methods such as BFGS can be derived as analytical solutions to certain nearest-matrix problems. In this article, we propose a similar idea for deriving new limited memory…

Optimization and Control · Mathematics 2024-03-06 Erik Berglund , Mikael Johansson

We propose a new stochastic L-BFGS algorithm and prove a linear convergence rate for strongly convex and smooth functions. Our algorithm draws heavily from a recent stochastic variant of L-BFGS proposed in Byrd et al. (2014) as well as a…

Optimization and Control · Mathematics 2016-04-15 Philipp Moritz , Robert Nishihara , Michael I. Jordan

In continual learning, a learner has to keep learning from the data over its whole life time. A key issue is to decide what knowledge to keep and what knowledge to let go. In a neural network, this can be implemented by using a step-size…

Machine Learning · Computer Science 2024-02-01 Thomas Degris , Khurram Javed , Arsalan Sharifnassab , Yuxin Liu , Richard Sutton

This paper proposes a framework of L-BFGS based on the (approximate) second-order information with stochastic batches, as a novel approach to the finite-sum minimization problems. Different from the classical L-BFGS where stochastic batches…

Machine Learning · Computer Science 2018-07-17 Jie Liu , Yu Rong , Martin Takac , Junzhou Huang

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

We consider the development of practical stochastic quasi-Newton, and in particular Kronecker-factored block-diagonal BFGS and L-BFGS methods, for training deep neural networks (DNNs). In DNN training, the number of variables and components…

Machine Learning · Computer Science 2021-01-11 Donald Goldfarb , Yi Ren , Achraf Bahamou

Fractional Gradient Descent (FGD) offers a novel and promising way to accelerate optimization by incorporating fractional calculus into machine learning. Although FGD has shown encouraging initial results across various optimization tasks,…

Machine Learning · Computer Science 2025-10-22 Jan Sobotka , Petr Šimánek , Pavel Kordík

For solving a broad class of nonconvex programming problems on an unbounded constraint set, we provide a self-adaptive step-size strategy that does not include line-search techniques and establishes the convergence of a generic approach…

Optimization and Control · Mathematics 2022-12-14 Thang Tran Ngoc , Hai Trinh Ngoc

Policy learning for partially observed control tasks requires policies that can remember salient information from past observations. In this paper, we present a method for learning policies with internal memory for high-dimensional,…

Machine Learning · Computer Science 2015-09-24 Marvin Zhang , Zoe McCarthy , Chelsea Finn , Sergey Levine , Pieter Abbeel

This paper describes an extension of the BFGS and L-BFGS methods for the minimization of a nonlinear function subject to errors. This work is motivated by applications that contain computational noise, employ low-precision arithmetic, or…

Optimization and Control · Mathematics 2021-09-10 Hao-Jun Michael Shi , Yuchen Xie , Richard Byrd , Jorge Nocedal

The limited memory BFGS method (L-BFGS) of Liu and Nocedal (1989) is often considered to be the method of choice for continuous optimization when first- and/or second- order information is available. However, the use of L-BFGS can be…

Neural and Evolutionary Computing · Computer Science 2015-11-03 Ilya Loshchilov

We study computational and statistical aspects of learning Latent Markov Decision Processes (LMDPs). In this model, the learner interacts with an MDP drawn at the beginning of each epoch from an unknown mixture of MDPs. To sidestep known…

Machine Learning · Computer Science 2024-06-13 Fan Chen , Constantinos Daskalakis , Noah Golowich , Alexander Rakhlin

We study the problem of fine-tuning a language model (LM) for a target task by optimally using the information from $n$ auxiliary tasks. This problem has broad applications in NLP, such as targeted instruction tuning and data selection in…

Computation and Language · Computer Science 2025-06-03 Dongyue Li , Ziniu Zhang , Lu Wang , Hongyang R. Zhang

In this paper, we study and prove the non-asymptotic superlinear convergence rate of the Broyden class of quasi-Newton algorithms which includes the Davidon--Fletcher--Powell (DFP) method and the Broyden--Fletcher--Goldfarb--Shanno (BFGS)…

Optimization and Control · Mathematics 2021-12-02 Qiujiang Jin , Aryan Mokhtari

Policy gradient methods have shown success in learning control policies for high-dimensional dynamical systems. Their biggest downside is the amount of exploration they require before yielding high-performing policies. In a lifelong…

Machine Learning · Computer Science 2020-10-23 Jorge A. Mendez , Boyu Wang , Eric Eaton

The ability to learn continuously from an incoming data stream without catastrophic forgetting is critical for designing intelligent systems. Many existing approaches to continual learning rely on stochastic gradient descent and its…

Machine Learning · Computer Science 2021-03-16 Sandeep Madireddy , Angel Yanguas-Gil , Prasanna Balaprakash

Although first-order stochastic algorithms, such as stochastic gradient descent, have been the main force to scale up machine learning models, such as deep neural nets, the second-order quasi-Newton methods start to draw attention due to…

Optimization and Control · Mathematics 2020-11-03 Qianqian Tong , Guannan Liang , Xingyu Cai , Chunjiang Zhu , Jinbo Bi