English
Related papers

Related papers: Towards Understanding Gradient Approximation in Eq…

200 papers

Despite the widespread adoption of neural networks, their training dynamics remain poorly understood. We show experimentally that as the size of the dataset increases, a point forms where the magnitude of the gradient of the loss becomes…

Machine Learning · Computer Science 2024-07-23 Mark Lowell

Many popular policy gradient methods for reinforcement learning follow a biased approximation of the policy gradient known as the discounted approximation. While it has been shown that the discounted approximation of the policy gradient is…

Machine Learning · Computer Science 2023-01-10 Chris Nota

We study the gradient descent (GD) dynamics of a depth-2 linear neural network with a single input and output. We show that GD converges at an explicit linear rate to a global minimum of the training loss, even with a large stepsize --…

Machine Learning · Computer Science 2025-01-22 Pierfrancesco Beneventano , Blake Woodworth

We present a theory for simultaneous approximation of the score function and its derivatives, enabling the handling of data distributions with low-dimensional structure and unbounded support. Our approximation error bounds match those in…

Numerical Analysis · Mathematics 2025-12-30 Konstantin Yakovlev , Nikita Puchkin

Supervised training of deep neural nets typically relies on minimizing cross-entropy. However, in many domains, we are interested in performing well on metrics specific to the application. In this paper we propose a direct loss minimization…

Machine Learning · Computer Science 2016-06-03 Yang Song , Alexander G. Schwing , Richard S. Zemel , Raquel Urtasun

Forward Gradients - the idea of using directional derivatives in forward differentiation mode - have recently been shown to be utilizable for neural network training while avoiding problems generally associated with backpropagation gradient…

Machine Learning · Computer Science 2023-06-13 Louis Fournier , Stéphane Rivaud , Eugene Belilovsky , Michael Eickenberg , Edouard Oyallon

Neural network optimization remains one of the most consequential yet poorly understood challenges in modern AI research, where improvements in training algorithms can lead to enhanced feature learning in foundation models,…

Machine Learning · Computer Science 2025-12-23 Ansh Nagwekar

Recent work across many machine learning disciplines has highlighted that standard descent methods, even without explicit regularization, do not merely minimize the training error, but also exhibit an implicit bias. This bias is typically…

Machine Learning · Computer Science 2020-06-22 Ziwei Ji , Miroslav Dudík , Robert E. Schapire , Matus Telgarsky

We establish conditions under which gradient descent applied to fixed-width deep networks drives the logistic loss to zero, and prove bounds on the rate of convergence. Our analysis applies for smoothed approximations to the ReLU, such as…

Machine Learning · Statistics 2021-07-02 Niladri S. Chatterji , Philip M. Long , Peter L. Bartlett

Regularization plays an important role in generalization of deep neural networks, which are often prone to overfitting with their numerous parameters. L1 and L2 regularizers are common regularization tools in machine learning with their…

Machine Learning · Computer Science 2019-10-21 Dae Hoon Park , Chiu Man Ho , Yi Chang , Huaqing Zhang

In this paper, we adopt a probability distribution estimation perspective to explore the optimization mechanisms of supervised classification using deep neural networks. We demonstrate that, when employing the Fenchel-Young loss, despite…

Machine Learning · Computer Science 2025-04-01 Binchuan Qi , Wei Gong , Li Li

Understanding the power of depth in feed-forward neural networks is an ongoing challenge in the field of deep learning theory. While current works account for the importance of depth for the expressive power of neural-networks, it remains…

Machine Learning · Computer Science 2019-03-11 Eran Malach , Shai Shalev-Shwartz

The paper contributes to strengthening the relation between machine learning and the theory of differential equations. In this context, the inverse problem of fitting the parameters, and the initial condition of a differential equation to…

Machine Learning · Computer Science 2022-06-22 Imre Fekete , András Molnár , Péter L. Simon

Stochastic gradient descent is one of the most successful approaches for solving large-scale problems, especially in machine learning and statistics. At each iteration, it employs an unbiased estimator of the full gradient computed from one…

Numerical Analysis · Mathematics 2018-12-05 Bangti Jin , Xiliang Lu

Recent experiments have shown that deep networks can approximate solutions to high-dimensional PDEs, seemingly escaping the curse of dimensionality. However, questions regarding the theoretical basis for such approximations, including the…

Machine Learning · Computer Science 2021-07-07 Tanya Marwah , Zachary C. Lipton , Andrej Risteski

It is generally recognized that finite learning rate (LR), in contrast to infinitesimal LR, is important for good generalization in real-life deep nets. Most attempted explanations propose approximating finite-LR SGD with Ito Stochastic…

Machine Learning · Computer Science 2021-06-18 Zhiyuan Li , Sadhika Malladi , Sanjeev Arora

Neural networks can emulate nonlinear physical systems with high accuracy, yet they may produce physically-inconsistent results when violating fundamental constraints. Here, we introduce a systematic way of enforcing nonlinear analytic…

Computational Physics · Physics 2021-03-10 Tom Beucler , Michael Pritchard , Stephan Rasp , Jordan Ott , Pierre Baldi , Pierre Gentine

Recent research has used deep learning to develop partial differential equation (PDE) models in science and engineering. The functional form of the PDE is determined by a neural network, and the neural network parameters are calibrated to…

Machine Learning · Computer Science 2023-10-17 Justin Sirignano , Jonathan MacArt , Konstantinos Spiliopoulos

Aimed at explaining the surprisingly good generalization behavior of overparameterized deep networks, recent works have developed a variety of generalization bounds for deep learning, all based on the fundamental learning-theoretic…

Machine Learning · Computer Science 2021-10-19 Vaishnavh Nagarajan , J. Zico Kolter

As larger deep learning models are hard to interpret, there has been a recent focus on generating explanations of these black-box models. In contrast, we may have apriori explanations of how models should behave. In this paper, we formalize…

Machine Learning · Computer Science 2023-12-27 Rattana Pukdee , Dylan Sam , J. Zico Kolter , Maria-Florina Balcan , Pradeep Ravikumar