English
Related papers

Related papers: Over-Alignment vs Over-Fitting: The Role of Featur…

200 papers

Batch size scheduling (BSS) plays a critical role in large-scale deep learning training, influencing both optimization dynamics and computational efficiency. Yet, its theoretical foundations remain poorly understood. In this work, we show…

Machine Learning · Computer Science 2026-02-24 Jinbo Wang , Binghui Li , Zhanpeng Zhou , Mingze Wang , Yuxuan Sun , Jiaqi Zhang , Xunliang Cai , Lei Wu

A key challenge in building theoretical foundations for deep learning is the complex optimization dynamics of neural networks, resulting from the high-dimensional interactions between the large number of network parameters. Such non-trivial…

Machine Learning · Computer Science 2021-12-07 Mohammad Pezeshki , Amartya Mitra , Yoshua Bengio , Guillaume Lajoie

It is common practice in deep learning to use overparameterized networks and train for as long as possible; there are numerous studies that show, both theoretically and empirically, that such practices surprisingly do not unduly harm the…

Machine Learning · Computer Science 2020-03-05 Leslie Rice , Eric Wong , J. Zico Kolter

Meta-Learning (ML) has proven to be a useful tool for training Few-Shot Learning (FSL) algorithms by exposure to batches of tasks sampled from a meta-dataset. However, the standard training procedure overlooks the dynamic nature of the…

Machine Learning · Computer Science 2021-04-13 Mateusz Ochal , Massimiliano Patacchiola , Amos Storkey , Jose Vazquez , Sen Wang

Overfitting is one of the fundamental challenges when training convolutional neural networks and is usually identified by a diverging training and test loss. The underlying dynamics of how the flow of activations induce overfitting is…

Machine Learning · Computer Science 2021-04-14 Karim Huesmann , Luis Garcia Rodriguez , Lars Linsen , Benjamin Risse

Overfitting is one of the most common problems when training deep neural networks on comparatively small datasets. Here, we demonstrate that neural network activation sparsity is a reliable indicator for overfitting which we utilize to…

Machine Learning · Computer Science 2020-02-24 Karim Huesmann , Soeren Klemm , Lars Linsen , Benjamin Risse

This paper proposes a meta-learning approach to evolving a parametrized loss function, which is called Meta-Loss Network (MLN), for training the image classification learning on small datasets. In our approach, the MLN is embedded in the…

Artificial Intelligence · Computer Science 2023-10-31 Zhaoyang Hai , Xiabi Liu

Supervised fine-tuning (SFT) on domain-specific data is the dominant approach for adapting foundation models to specialized tasks. However, it has been observed that SFT models tend to forget knowledge acquired during pretraining. In vision…

Artificial Intelligence · Computer Science 2025-06-03 Yifan Hao , Xingyuan Pan , Hanning Zhang , Chenlu Ye , Rui Pan , Tong Zhang

Neural networks trained via gradient descent with random initialization and without any regularization enjoy good generalization performance in practice despite being highly overparametrized. A promising direction to explain this phenomenon…

Machine Learning · Computer Science 2022-05-17 Hancheng Min , Salma Tarmoun , Rene Vidal , Enrique Mallada

The modern strategy for training deep neural networks for classification tasks includes optimizing the network's weights even after the training error vanishes to further push the training loss toward zero. Recently, a phenomenon termed…

Machine Learning · Computer Science 2022-10-13 Tom Tirer , Joan Bruna

Federated learning (FL) is a new paradigm for distributed machine learning that allows a global model to be trained across multiple clients without compromising their privacy. Although FL has demonstrated remarkable success in various…

Machine Learning · Computer Science 2023-06-06 Haolin Wang , Xuefeng Liu , Jianwei Niu , Shaojie Tang , Jiaxing Shen

Deep neural networks have achieved remarkable success in practice, yet a mechanistic understanding of how features evolve during training remains incomplete, especially in the large-depth limit. For ResNets under depth-$\mu$P scaling, prior…

Machine Learning · Computer Science 2026-05-28 Zihan Yao , Ruoyu Wu , Tianxiang Gao

Fine-tuning Large Language Models (LLMs) on specific datasets is a common practice to improve performance on target tasks. However, this performance gain often leads to overfitting, where the model becomes too specialized in either the task…

Computation and Language · Computer Science 2024-09-10 Sonam Gupta , Yatin Nandwani , Asaf Yehudai , Mayank Mishra , Gaurav Pandey , Dinesh Raghu , Sachindra Joshi

This paper explores a scientific question in supervised fine-tuning (SFT): why SFT is broadly effective for small-scale deep neural networks, yet can produce inconsistent or even detrimental effects when applied to large language models…

Artificial Intelligence · Computer Science 2026-05-19 Junpeng Zhang , Lei Cheng , Guoxi Zhang , Hua Cai , Qing Xu , Quanshi Zhang

Training modern large language models (LLMs) has become a veritable smorgasbord of algorithms and datasets designed to elicit particular behaviors, making it critical to develop techniques to understand the effects of datasets on the…

Machine Learning · Computer Science 2026-02-05 Ishaq Aden-Ali , Noah Golowich , Allen Liu , Abhishek Shetty , Ankur Moitra , Nika Haghtalab

We formalize and study a phenomenon called feature collapse that makes precise the intuitive idea that entities playing a similar role in a learning task receive similar representations. As feature collapse requires a notion of task, we…

Machine Learning · Computer Science 2023-05-26 Thomas Laurent , James H. von Brecht , Xavier Bresson

Traditional scaling laws in natural language processing suggest that increasing model size and training data enhances performance. However, recent studies reveal deviations, particularly in large language models, where performance…

Machine Learning · Computer Science 2025-07-16 Zhengyu Chen , Siqi Wang , Teng Xiao , Yudong Wang , Shiqi Chen , Xunliang Cai , Junxian He , Jingang Wang

We perform an average case analysis of the generalization dynamics of large neural networks trained using gradient descent. We study the practically-relevant "high-dimensional" regime where the number of free parameters in the network is on…

Machine Learning · Statistics 2017-10-11 Madhu S. Advani , Andrew M. Saxe

In-context learning (ICL), which promotes inference with several demonstrations, has become a widespread paradigm to stimulate LLM capabilities for downstream tasks. Due to context length constraints, it cannot be further improved in spite…

Computation and Language · Computer Science 2024-06-04 Jiahao Li , Quan Wang , Licheng Zhang , Guoqing Jin , Zhendong Mao

Reinforcement learning (RL) is a key post-pretraining step for aligning large language models (LLMs) with complex tasks and human preferences. While it is often assumed that RL fine-tuning requires updating most of a model's parameters, we…

Machine Learning · Computer Science 2025-07-30 Andrii Balashov