English
Related papers

Related papers: Investigating the interaction between gradient-onl…

200 papers

Neural networks trained to minimize the logistic (a.k.a. cross-entropy) loss with gradient-based methods are observed to perform well in many supervised classification tasks. Towards understanding this phenomenon, we analyze the training…

Optimization and Control · Mathematics 2020-06-23 Lenaic Chizat , Francis Bach

A wide variety of activation functions have been proposed for neural networks. The Rectified Linear Unit (ReLU) is especially popular today. There are many practical reasons that motivate the use of the ReLU. This paper provides new…

Machine Learning · Statistics 2020-10-19 Rahul Parhi , Robert D. Nowak

Gradient descent typically converges to a single minimum of the training loss without mechanisms to explore alternative minima that may generalize better. Searching for diverse minima directly in high-dimensional parameter space is…

Machine Learning · Computer Science 2025-09-16 Akshay Vegesna , Samip Dahal

Activation functions play a significant role in neural network design by enabling non-linearity. The choice of activation function was previously shown to influence the properties of the resulting loss landscape. Understanding the…

Machine Learning · Computer Science 2023-06-29 Anna Sergeevna Bosman , Andries Engelbrecht , Marde Helbig

Differentiable architecture search (DARTS) has emerged as a promising technique for effective neural architecture search, and it mainly contains two steps to find the high-performance architecture: First, the DARTS supernet that consists of…

Artificial Intelligence · Computer Science 2024-09-24 Le Yang , Ziwei Zheng , Yizeng Han , Shiji Song , Gao Huang , Fan Li

Implicit deep learning has recently become popular in the machine learning community since these implicit models can achieve competitive performance with state-of-the-art deep networks while using significantly less memory and computational…

Machine Learning · Computer Science 2022-05-17 Tianxiang Gao , Hongyang Gao

Gaussian Error Linear Unit (GELU) is a widely used smooth alternative to Rectifier Linear Unit (ReLU), yet many deployment, compression, and analysis toolchains are most naturally expressed for piecewise-linear (ReLU-type) networks. We…

In this work, we investigate a particular implicit bias in gradient descent training, which we term "Feature Averaging," and argue that it is one of the principal factors contributing to the non-robustness of deep neural networks. We show…

Machine Learning · Computer Science 2025-03-04 Binghui Li , Zhixuan Pan , Kaifeng Lyu , Jian Li

Deep learning models are often successfully trained using gradient descent, despite the worst case hardness of the underlying non-convex optimization problem. The key question is then under what conditions can one prove that optimization…

Machine Learning · Computer Science 2017-02-28 Alon Brutzkus , Amir Globerson

It is generally thought that the use of stochastic activation functions in deep learning architectures yield models with superior generalization abilities. However, a sufficiently rigorous statement and theoretical proof of this heuristic…

Machine Learning · Computer Science 2024-06-25 Sriram Nagaraj , Truman Hickok

We consider the problem of learning the best-fitting single neuron as measured by the expected square loss $\mathbb{E}_{(x,y)\sim \mathcal{D}}[(\sigma(w^\top x)-y)^2]$ over some unknown joint distribution $\mathcal{D}$ by using gradient…

Machine Learning · Computer Science 2020-09-01 Spencer Frei , Yuan Cao , Quanquan Gu

Despite the fact that the loss functions of deep neural networks are highly non-convex, gradient-based optimization algorithms converge to approximately the same performance from many random initial points. One thread of work has focused on…

Machine Learning · Computer Science 2020-03-24 Charles G. Frye , James Simon , Neha S. Wadia , Andrew Ligeralde , Michael R. DeWeese , Kristofer E. Bouchard

There has been a large literature of neural architecture search, but most existing work made use of heuristic rules that largely constrained the search flexibility. In this paper, we first relax these manually designed constraints and…

Computer Vision and Pattern Recognition · Computer Science 2020-07-08 Kaifeng Bi , Lingxi Xie , Xin Chen , Longhui Wei , Qi Tian

In the field of machine learning, comprehending the intricate training dynamics of neural networks poses a significant challenge. This paper explores the training dynamics of neural networks, particularly whether these dynamics can be…

Machine Learning · Computer Science 2024-08-16 Yeachan Park

Understanding the optimization dynamics of neural networks is necessary for closing the gap between theory and practice. Stochastic first-order optimization algorithms are known to efficiently locate favorable minima in deep neural…

Machine Learning · Computer Science 2023-06-22 Charles Guille-Escuret , Hiroki Naganuma , Kilian Fatras , Ioannis Mitliagkas

Mini-batch sub-sampling in neural network training is unavoidable, due to growing data demands, memory-limited computational resources such as graphical processing units (GPUs), and the dynamics of on-line learning. In this study we…

Machine Learning · Statistics 2020-04-07 Dominic Kafka , Daniel Wilke

We show that gating mechanisms in recurrent neural networks (RNNs) induce lag-dependent and direction-dependent effective learning rates, even when training uses a fixed, global step size. This behavior arises from a coupling between…

Machine Learning · Computer Science 2026-04-22 Lorenzo Livi

Efficient performance estimation of architectures drawn from large search spaces is essential to Neural Architecture Search. One-Shot methods tackle this challenge by training one supernet to approximate the performance of every…

Computer Vision and Pattern Recognition · Computer Science 2022-04-06 Shoukang Hu , Ruochen Wang , Lanqing Hong , Zhenguo Li , Cho-Jui Hsieh , Jiashi Feng

Neural networks trained with standard objectives exhibit behaviors characteristic of probabilistic inference: soft clustering, prototype specialization, and Bayesian uncertainty tracking. These phenomena appear across architectures -- in…

Machine Learning · Computer Science 2026-01-01 Alan Oursland

Training loss and throughput can hide distinct internal representation in language-model training. To examine these hidden mechanics, we use spectral measurements as practical and operational diagnostics. Using a controlled family of…

Machine Learning · Statistics 2026-05-08 Andy Zeyi Liu , Elliot Paquette , John Sous
‹ Prev 1 3 4 5 6 7 10 Next ›