English
Related papers

Related papers: Learning Rate Engineering: From Coarse Single Para…

200 papers

Learning rate configuration is a fundamental aspect of modern deep learning. The prevailing practice of applying a uniform learning rate across all layers overlooks the structural heterogeneity of Transformers, potentially limiting their…

Machine Learning · Computer Science 2026-05-28 Di He , Songjun Tu , Keyu Wang , Lu Yin , Shiwei Liu

The choice of step-size used in Stochastic Gradient Descent (SGD) optimization is empirically selected in most training procedures. Moreover, the use of scheduled learning techniques such as Step-Decaying, Cyclical-Learning, and Warmup to…

Machine Learning · Computer Science 2020-06-12 Mahdi S. Hosseini , Konstantinos N. Plataniotis

Continual Learning (CL) methods have traditionally focused on mitigating catastrophic forgetting through gradient-based retraining, an approach ill-suited for deployed agents that must adapt in real time. We introduce our Adaptive Teaching…

Machine Learning · Computer Science 2025-11-04 Aman Jaglan , Jarrod Barnes

Learning rate schedules used in practice bear little resemblance to those recommended by theory. We close much of this theory/practice gap, and as a consequence are able to derive new problem-adaptive learning rate schedules. Our main…

Machine Learning · Computer Science 2024-10-31 Aaron Defazio , Ashok Cutkosky , Harsh Mehta , Konstantin Mishchenko

Increasing the batch size of a deep learning model is a challenging task. Although it might help in utilizing full available system memory during training phase of a model, it results in significant loss of test accuracy most often. LARS…

Machine Learning · Computer Science 2021-02-08 Kanchan Chowdhury , Ankita Sharma , Arun Deepak Chandrasekar

Deep Neural Networks (DNNs) are extremely computationally demanding, which presents a large barrier to their deployment on resource-constrained devices. Since such devices are where many emerging deep learning applications lie (e.g.,…

Machine Learning · Computer Science 2023-11-16 Perry Gibson , José Cano , Elliot J. Crowley , Amos Storkey , Michael O'Boyle

Despite large language models (LLMs) have achieved impressive achievements across numerous tasks, supervised fine-tuning (SFT) remains essential for adapting these models to specialized domains. However, SFT for domain specialization can be…

Computation and Language · Computer Science 2025-11-13 Yibai Liu , Shihang Wang , Zeming Liu , Zheming Song , Junzhe Wang , Jingjing Liu , Qingjie Liu , Yunhong Wang

In deep Reinforcement Learning (RL), the learning rate critically influences both stability and performance, yet its optimal value shifts during training as the environment and policy evolve. Standard decay schedulers assume monotonic…

Machine Learning · Computer Science 2025-10-09 Henrique Donâncio , Antoine Barrier , Leah F. South , Florence Forbes

We propose an algorithm for the adaptation of the learning rate for stochastic gradient descent (SGD) that avoids the need for validation set use. The idea for the adaptiveness comes from the technique of extrapolation: to get an estimate…

Machine Learning · Statistics 2020-08-28 Antti Koskela , Antti Honkela

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

Multi-task reinforcement learning (MTRL) aims to train a single agent to efficiently optimize performance across multiple tasks simultaneously. However, jointly optimizing all tasks often yields imbalanced learning: agents quickly solve…

Machine Learning · Computer Science 2026-05-15 Nicholas E. Corrado , Wenyuan Huang , Josiah P. Hanna

In this paper, we attempt to address the challenge of applying Neural Architecture Search (NAS) algorithms, specifically the Differentiable Architecture Search (DARTS), to long-tailed datasets where class distribution is highly imbalanced.…

Machine Learning · Computer Science 2024-06-12 Chenxia Tang

In this work, we propose new adaptive step size strategies that improve several stochastic gradient methods. Our first method (StoPS) is based on the classical Polyak step size (Polyak, 1987) and is an extension of the recent development of…

Machine Learning · Computer Science 2022-08-11 Samuel Horváth , Konstantin Mishchenko , Peter Richtárik

Machine/deep learning models have been widely adopted for predicting the configuration performance of software systems. However, a crucial yet unaddressed challenge is how to cater for the sparsity inherited from the configuration…

Software Engineering · Computer Science 2024-11-21 Jingzhi Gong , Tao Chen , Rami Bahsoon

Unlike areas such as computer vision and speech recognition where convolutional and recurrent neural networks-based approaches have proven effective to the nature of the respective areas of application, deep learning (DL) still lacks a…

Signal Processing · Electrical Eng. & Systems 2021-05-14 Khalid Youssef , Greg Schuette , Yubin Cai , Daisong Zhang , Yikun Huang , Yahya Rahmat-Samii , Louis-S. Bouchard

Test Time Adaptation (TTA) addresses the problem of distribution shift by adapting a pretrained model to a new domain during inference. When faced with challenging shifts, most methods collapse and perform worse than the original pretrained…

Machine Learning · Computer Science 2025-02-25 Sabyasachi Sahoo , Mostafa ElAraby , Jonas Ngnawe , Yann Pequignot , Frederic Precioso , Christian Gagne

Determinism is indispensable for reproducibility in large language model (LLM) training, yet it often exacts a steep performance cost. In widely used attention implementations such as FlashAttention-3, the deterministic backward pass can…

Machine Learning · Computer Science 2026-01-30 Xinwei Qiang , Hongmin Chen , Shixuan Sun , Jingwen Leng , Xin Liu , Minyi Guo

Recently many first and second order variants of SGD have been proposed to facilitate training of Deep Neural Networks (DNNs). A common limitation of these works stem from the fact that they use the same learning rate across all instances…

Machine Learning · Computer Science 2021-05-31 Shreyas Saxena , Nidhi Vyas , Dennis DeCoste

Large language models (LLMs) have shown remarkable reasoning capabilities, yet aligning such abilities to small language models (SLMs) remains a challenge due to distributional mismatches and limited model capacity. Existing reasoning…

Computation and Language · Computer Science 2025-05-28 Yong Wu , Weihang Pan , Ke Li , Chen Binhui , Ping Li , Binbin Lin

We study the fundamental optimization principles of self-attention, the defining mechanism of transformers, by analyzing the implicit bias of gradient-based optimizers in training a self-attention layer with a linear decoder in binary…

Machine Learning · Computer Science 2025-04-01 Bhavya Vasudeva , Puneesh Deora , Christos Thrampoulidis
‹ Prev 1 2 3 10 Next ›