English
Related papers

Related papers: Nexus: Same Pretraining Loss, Better Downstream Ge…

200 papers

Data mixing--the strategic reweighting of training domains--is a critical component in training robust machine learning models. This problem is naturally formulated as a bilevel optimization task, where the outer loop optimizes domain…

Machine Learning · Computer Science 2026-02-24 Rudrajit Das , Neel Patel , Meisam Razaviyayn , Vahab Mirrokni

A recent line of research has shown that gradient-based algorithms with random initialization can converge to the global minima of the training loss for over-parameterized (i.e., sufficiently wide) deep neural networks. However, the…

Machine Learning · Computer Science 2019-06-12 Difan Zou , Quanquan Gu

A core issue with learning to optimize neural networks has been the lack of generalization to real world problems. To address this, we describe a system designed from a generalization-first perspective, learning to update optimizer…

Machine Learning · Computer Science 2021-06-09 Diogo Almeida , Clemens Winter , Jie Tang , Wojciech Zaremba

This dissertation studies a fundamental open challenge in deep learning theory: why do deep networks generalize well even while being overparameterized, unregularized and fitting the training data to zero error? In the first part of the…

Machine Learning · Computer Science 2021-10-19 Vaishnavh Nagarajan

We study stochastic optimization of nonconvex loss functions, which are typical objectives for training neural networks. We propose stochastic approximation algorithms which optimize a series of regularized, nonlinearized losses on large…

Machine Learning · Computer Science 2019-03-12 Weiran Wang , Nathan Srebro

In this paper, we introduce weight prediction into the AdamW optimizer to boost its convergence when training the deep neural network (DNN) models. In particular, ahead of each mini-batch training, we predict the future weights according to…

Machine Learning · Computer Science 2023-08-09 Lei Guan

Due to the nonlinear nature of Deep Neural Networks (DNNs), one can not guarantee convergence to a unique global minimum of the loss when using optimizers relying only on local information, such as SGD. Indeed, this was a primary source of…

Stochastic gradient descent (SGD) is almost ubiquitously used for training non-convex optimization tasks. Recently, a hypothesis proposed by Keskar et al. [2017] that large batch methods tend to converge to sharp minimizers has received…

Machine Learning · Statistics 2018-12-04 Xiaowu Dai , Yuhua Zhu

The goal of this thesis is to develop the optimisation and generalisation theoretic foundations of learning in artificial neural networks. On optimisation, a new theoretical framework is proposed for deriving architecture-dependent…

Neural and Evolutionary Computing · Computer Science 2022-10-20 Jeremy Bernstein

Post-training quantization is widely employed to reduce the computational demands of neural networks. Typically, individual substructures, such as layers or blocks of layers, are quantized with the objective of minimizing quantization…

Machine Learning · Computer Science 2024-11-07 Khasmamad Shabanovi , Lukas Wiest , Vladimir Golkov , Daniel Cremers , Thomas Pfeil

We demonstrate that explicitly aligning the pretraining objectives to the finetuning objectives in language model training significantly improves the finetuning task performance and reduces the minimum amount of finetuning examples…

Computation and Language · Computer Science 2020-02-07 Nuo Wang Pierse , Jingwen Lu

In this paper, we propose a general deep learning training framework XGrad which introduces weight prediction into the popular gradient-based optimizers to boost their convergence and generalization when training the deep neural network…

Machine Learning · Computer Science 2024-04-09 Lei Guan , Dongsheng Li , Yanqi Shi , Jian Meng

For most languages of the world, language model pre-training operates in a data-constrained regime where models must repeat their training data many times, degrading generalization. Two remedies exist: aggressive hyperparameter tuning such…

Machine Learning · Computer Science 2026-05-14 Paul Jeha , Anastasiia Sedova , Louis Béthune , Skyler Seto , Jes Frellsen , Pierre Ablin , Natalie Schluter

In this work, we propose a notion of practical learnability grounded in finite sample settings, and develop a conjugate learning theoretical framework based on convex conjugate duality to characterize this learnability property. Building on…

Machine Learning · Statistics 2026-02-20 Binchuan Qi

In this work, we investigate whether small language models can determine high-quality subsets of large-scale text datasets that improve the performance of larger language models. While existing work has shown that pruning based on the…

Machine Learning · Computer Science 2024-06-03 Zachary Ankner , Cody Blakeney , Kartik Sreenivasan , Max Marion , Matthew L. Leavitt , Mansheej Paul

Large Language Models (LLMs) demonstrate exceptional reasoning abilities, enabling strong generalization across diverse tasks such as commonsense reasoning and instruction following. However, as LLMs scale, inference costs become…

Computation and Language · Computer Science 2025-02-06 Rhea Sanjay Sukthanker , Benedikt Staffler , Frank Hutter , Aaron Klein

As language models scale, the amount of data they require grows -- yet many target data sources, such as low-resource languages or specialized domains, are inherently limited in size. A common strategy is to mix this scarce but valuable…

Machine Learning · Computer Science 2026-05-18 Anastasiia Sedova , Skyler Seto , Natalie Schluter , Pierre Ablin

It is widely observed that deep learning models with learned parameters generalize well, even with much more model parameters than the number of training samples. We systematically investigate the underlying reasons why deep neural networks…

Machine Learning · Computer Science 2017-11-29 Lei Wu , Zhanxing Zhu , Weinan E

Decentralized training of deep neural networks has attracted significant attention for its theoretically superior scalability over synchronous data-parallel methods like All-Reduce. However, realizing this potential in multi-node training…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-10-17 Zesen Wang , Jiaojiao Zhang , Xuyang Wu , Mikael Johansson

Asynchronous distributed algorithms are a popular way to reduce synchronization costs in large-scale optimization, and in particular for neural network training. However, for nonsmooth and nonconvex objectives, few convergence guarantees…

Optimization and Control · Mathematics 2020-07-14 Vyacheslav Kungurtsev , Malcolm Egan , Bapi Chatterjee , Dan Alistarh
‹ Prev 1 3 4 5 6 7 10 Next ›