English
Related papers

Related papers: Maximal Initial Learning Rates in Deep ReLU Networ…

200 papers

It is common in deep learning to warm up the learning rate $\eta$, often by a linear schedule between $\eta_{\text{init}} = 0$ and a predetermined target $\eta_{\text{trgt}}$. In this paper, we show through systematic experiments using SGD…

Machine Learning · Computer Science 2024-11-05 Dayal Singh Kalra , Maissam Barkeshli

We prove several hardness results for training depth-2 neural networks with the ReLU activation function; these networks are simply weighted sums (that may include negative coefficients) of ReLUs. Our goal is to output a depth-2 neural…

Machine Learning · Computer Science 2020-11-30 Surbhi Goel , Adam Klivans , Pasin Manurangsi , Daniel Reichman

It is generally accepted that starting neural networks training with large learning rates (LRs) improves generalization. Following a line of research devoted to understanding this effect, we conduct an empirical study in a controlled…

Machine Learning · Computer Science 2024-10-30 Ildus Sadrtdinov , Maxim Kodryan , Eduard Pokonechny , Ekaterina Lobacheva , Dmitry Vetrov

The choice of initial learning rate can have a profound effect on the performance of deep networks. We present a class of neural networks with solvable training dynamics, and confirm their predictions empirically in practical deep learning…

Machine Learning · Statistics 2020-03-05 Aitor Lewkowycz , Yasaman Bahri , Ethan Dyer , Jascha Sohl-Dickstein , Guy Gur-Ari

In this short note we consider random fully connected ReLU networks of width $n$ and depth $L$ equipped with a mean-field weight initialization. Our purpose is to study the dependence on $n$ and $L$ of the maximal update ($\mu$P) learning…

Machine Learning · Computer Science 2023-05-16 Samy Jelassi , Boris Hanin , Ziwei Ji , Sashank J. Reddi , Srinadh Bhojanapalli , Sanjiv Kumar

We systematically analyze optimization dynamics in deep neural networks (DNNs) trained with stochastic gradient descent (SGD) and study the effect of learning rate $\eta$, depth $d$, and width $w$ of the neural network. By analyzing the…

Machine Learning · Computer Science 2023-10-25 Dayal Singh Kalra , Maissam Barkeshli

The success of deep networks has been attributed in part to their expressivity: per parameter, deep networks can approximate a richer class of functions than shallow networks. In ReLU networks, the number of activation patterns is one…

Machine Learning · Statistics 2019-10-22 Boris Hanin , David Rolnick

Inspired by recent research that recommends starting neural networks training with large learning rates (LRs) to achieve the best generalization, we explore this hypothesis in detail. Our study clarifies the initial LR ranges that provide…

Machine Learning · Computer Science 2023-11-21 Ekaterina Lobacheva , Eduard Pockonechnyy , Maxim Kodryan , Dmitry Vetrov

Deep neural networks have been used in various machine learning applications and achieved tremendous empirical successes. However, training deep neural networks is a challenging task. Many alternatives have been proposed in place of…

Machine Learning · Computer Science 2020-09-09 Yeonjong Shin

Deep learning relies on good initialization schemes and hyperparameter choices prior to training a neural network. Random weight initializations induce random network ensembles, which give rise to the trainability, training speed, and…

Machine Learning · Statistics 2019-10-25 Rebekka Burkholz , Alina Dubatovka

One of the arguments to explain the success of deep learning is the powerful approximation capacity of deep neural networks. Such capacity is generally accompanied by the explosive growth of the number of parameters, which, in turn, leads…

Machine Learning · Computer Science 2022-09-15 Zuowei Shen , Haizhao Yang , Shijun Zhang

In a neural network with ReLU activations, the number of piecewise linear regions in the output can grow exponentially with depth. However, this is highly unlikely to happen when the initial parameters are sampled randomly, which therefore…

Machine Learning · Computer Science 2025-10-17 Max Milkert , David Hyde , Forrest Laine

"Deep Learning"/"Deep Neural Nets" is a technological marvel that is now increasingly deployed at the cutting-edge of artificial intelligence tasks. This dramatic success of deep learning in the last few years has been hinged on an enormous…

Machine Learning · Computer Science 2021-04-30 Anirbit Mukherjee

We study the average robustness notion in deep neural networks in (selected) wide and narrow, deep and shallow, as well as lazy and non-lazy training settings. We prove that in the under-parameterized setting, width has a negative effect…

Machine Learning · Computer Science 2023-02-13 Zhenyu Zhu , Fanghui Liu , Grigorios G Chrysos , Volkan Cevher

Recent studies have shown that high disparities in effective learning rates (ELRs) across layers in deep neural networks can negatively affect trainability. We formalize how these disparities evolve over time by modeling weight dynamics…

Machine Learning · Computer Science 2024-05-27 Christian H. X. Ali Mehmeti-Göpel , Michael Wand

We develop a new theoretical framework to analyze the generalization error of deep learning, and derive a new fast learning rate for two representative algorithms: empirical risk minimization and Bayesian deep learning. The series of…

Statistics Theory · Mathematics 2017-05-31 Taiji Suzuki

We prove that, for the fundamental regression task of learning a single neuron, training a one-hidden layer ReLU network of any width by gradient flow from a small initialisation converges to zero loss and is implicitly biased to minimise…

Machine Learning · Computer Science 2023-10-03 Dmitry Chistikov , Matthias Englert , Ranko Lazic

Training neural networks on image datasets generally require extensive experimentation to find the optimal learning rate regime. Especially, for the cases of adversarial training or for training a newly synthesized model, one would not know…

Machine Learning · Computer Science 2019-10-28 Koyel Mukherjee , Alind Khare , Ashish Verma

Training neural networks with first order optimisation methods is at the core of the empirical success of deep learning. The scale of initialisation is a crucial factor, as small initialisations are generally associated to a feature…

Machine Learning · Computer Science 2025-09-16 Etienne Boursier , Nicolas Flammarion

One of the mysteries in the success of neural networks is randomly initialized first order methods like gradient descent can achieve zero training loss even though the objective function is non-convex and non-smooth. This paper demystifies…

Machine Learning · Computer Science 2019-02-06 Simon S. Du , Xiyu Zhai , Barnabas Poczos , Aarti Singh
‹ Prev 1 2 3 10 Next ›