English
Related papers

Related papers: Unintended Effects on Adaptive Learning Rate for T…

200 papers

Most learning algorithms are not invariant to the scale of the function that is being approximated. We propose to adaptively normalize the targets used in learning. This is useful in value-based reinforcement learning, where the magnitude…

Machine Learning · Computer Science 2016-08-17 Hado van Hasselt , Arthur Guez , Matteo Hessel , Volodymyr Mnih , David Silver

The capacity of meta-learning algorithms to quickly adapt to a variety of tasks, including ones they did not experience during meta-training, has been a key factor in the recent success of these methods on few-shot learning problems. This…

Machine Learning · Computer Science 2018-12-06 Tristan Deleu , Yoshua Bengio

We study the scaling of classification error rates with respect to the size of the training dataset. In contrast to classical results where rates are minimax optimal for a problem class, this work starts with the empirical observation that,…

Machine Learning · Statistics 2025-06-04 Pengkun Yang , Jingzhao Zhang

Stochastic gradient descent with a large initial learning rate is widely used for training modern neural net architectures. Although a small initial learning rate allows for faster training and better test performance initially, the large…

Machine Learning · Computer Science 2020-04-28 Yuanzhi Li , Colin Wei , Tengyu Ma

Mixed-effects models fit to observational practice data are widely used in learning analytics to estimate student-level variation in initial knowledge and learning rate, and the resulting estimates increasingly inform substantive claims…

Computers and Society · Computer Science 2026-05-19 Hansol Lee , Guilherme Lichand , Cristina Barnard , Lucas Klotz , Candace Thille , Yunsung Kim , Benjamin W. Domingue

Artificial neural network training with stochastic gradient descent can be destabilized by "bad batches" with high losses. This is often problematic for training with small batch sizes, high order loss functions or unstably high learning…

Machine Learning · Computer Science 2020-05-21 Jeffrey M. Ede , Richard Beanland

In this work, multiplicative stochasticity is applied to the learning rate of stochastic optimization algorithms, giving rise to stochastic learning-rate schemes. In-expectation theoretical convergence results of Stochastic Gradient Descent…

Optimization and Control · Mathematics 2022-03-22 Theodoros Mamalis , Dusan Stipanovic , Petros Voulgaris

In scalable machine learning systems, model training is often parallelized over multiple nodes that run without tight synchronization. Most analysis results for the related asynchronous algorithms use an upper bound on the information…

Machine Learning · Computer Science 2022-04-12 Xuyang Wu , Sindri Magnusson , Hamid Reza Feyzmahdavian , Mikael Johansson

We introduce a new class of adaptive non-linear autoregressive (Nlar) models incorporating the concept of momentum, which dynamically estimate both the learning rates and momentum as the number of iterations increases. In our method, the…

Machine Learning · Computer Science 2024-12-03 Ramin Okhrati

Scaling laws in deep learning -- empirical power-law relationships linking model performance to resource growth -- have emerged as simple yet striking regularities across architectures, datasets, and tasks. These laws are particularly…

Machine Learning · Computer Science 2026-05-01 Francesco D'Amico , Dario Bocchi , Matteo Negri

In adaptive dynamic programming, neurocontrol and reinforcement learning, the objective is for an agent to learn to choose actions so as to minimise a total cost function. In this paper we show that when discretized time is used to model…

Machine Learning · Computer Science 2013-02-25 Michael Fairbank

Recent analyses of certain gradient descent optimization methods have shown that performance can degrade in some settings - such as with stochasticity or implicit momentum. In deep reinforcement learning (Deep RL), such optimization methods…

Machine Learning · Computer Science 2018-10-08 Peter Henderson , Joshua Romoff , Joelle Pineau

Sharing parameters in multi-agent deep reinforcement learning has played an essential role in allowing algorithms to scale to a large number of agents. Parameter sharing between agents significantly decreases the number of trainable…

Multiagent Systems · Computer Science 2021-06-15 Filippos Christianos , Georgios Papoudakis , Arrasy Rahman , Stefano V. Albrecht

In this work, we provide a large-scale empirical study of the scaling properties of multilingual neural machine translation models. We examine how increases in the model size affect the model performance and investigate the role of the…

Computation and Language · Computer Science 2023-02-21 Patrick Fernandes , Behrooz Ghorbani , Xavier Garcia , Markus Freitag , Orhan Firat

Optimization plays a key role in the training of deep neural networks. Deciding when to stop training can have a substantial impact on the performance of the network during inference. Under certain conditions, the generalization error can…

Machine Learning · Computer Science 2021-09-20 Florian Dubost , Erin Hong , Max Pike , Siddharth Sharma , Siyi Tang , Nandita Bhaskhar , Christopher Lee-Messer , Daniel Rubin

We consider neural networks (NNs) where the final layer is down-scaled by a fixed hyperparameter $\gamma$. Recent work has identified $\gamma$ as controlling the strength of feature learning. As $\gamma$ increases, network evolution changes…

Machine Learning · Computer Science 2025-03-04 Alexander Atanasov , Alexandru Meterez , James B. Simon , Cengiz Pehlevan

Commonly used optimization algorithms often show a trade-off between good generalization and fast training times. For instance, stochastic gradient descent (SGD) tends to have good generalization; however, adaptive gradient methods have…

Machine Learning · Computer Science 2023-06-14 Aditya Cowsik , Tankut Can , Paolo Glorioso

In this work we analyze strategies for convolutional neural network scaling; that is, the process of scaling a base convolutional network to endow it with greater computational complexity and consequently representational power. Example…

Computer Vision and Pattern Recognition · Computer Science 2021-03-12 Piotr Dollár , Mannat Singh , Ross Girshick

We provide a theoretical explanation for the effectiveness of gradient clipping in training deep neural networks. The key ingredient is a new smoothness condition derived from practical neural network training examples. We observe that…

Optimization and Control · Mathematics 2020-02-12 Jingzhao Zhang , Tianxing He , Suvrit Sra , Ali Jadbabaie

We investigate the neural Actor Critic algorithm using shallow neural networks for both the Actor and Critic models. The focus of this work is twofold: first, to compare the convergence properties of the network outputs under various…

Machine Learning · Computer Science 2026-01-27 Nikos Georgoudios , Konstantinos Spiliopoulos , Justin Sirignano