English
Related papers

Related papers: Learning compositional functions via multiplicativ…

200 papers

We propose NovoGrad, an adaptive stochastic gradient descent method with layer-wise gradient normalization and decoupled weight decay. In our experiments on neural networks for image classification, speech recognition, machine translation,…

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

Federated Learning is a popular distributed learning paradigm in machine learning. Meanwhile, composition optimization is an effective hierarchical learning model, which appears in many machine learning applications such as meta learning…

Machine Learning · Computer Science 2023-03-31 Feihu Huang

Stochastic gradient descent-based algorithms are widely used for training deep neural networks but often suffer from slow convergence. To address the challenge, we leverage the framework of the alternating direction method of multipliers…

Machine Learning · Computer Science 2025-02-03 Ouya Wang , Shenglong Zhou , Geoffrey Ye Li

In this paper, we propose a novel accelerated stochastic gradient method with momentum, which momentum is the weighted average of previous gradients. The weights decays inverse proportionally with the iteration times. Stochastic gradient…

Machine Learning · Computer Science 2020-06-02 Liang Liu , Xiaopeng Luo

The impressive performance of large language models (LLMs) arises from their massive scale and heterogeneous module composition. However, this structural heterogeneity introduces additional optimization challenges. While adaptive optimizers…

Machine Learning · Computer Science 2026-05-08 Ziqing Wen , Zhouyang Liu , Jiahuan Wang , Ping Luo , Li Shen , Dongsheng Li , Tao Sun

We present a novel method for learning the weights of an artificial neural network - a Message Passing Learning Protocol (MPLP). In MPLP, we abstract every operations occurring in ANNs as independent agents. Each agent is responsible for…

Machine Learning · Computer Science 2020-07-06 Ettore Randazzo , Eyvind Niklasson , Alexander Mordvintsev

We propose ADAPT, a meta-learning algorithm that \emph{learns} task sampling proportions under an explicit token budget for multi-task instruction tuning. Instead of fixing task weights by hand, \adapt{} maintains a continuous distribution…

Computation and Language · Computer Science 2025-12-05 Pritam Kadasi , Abhishek Upperwal , Mayank SIngh

Discrete-time modeling of acoustic, mechanical and electrical systems is a prominent topic in the musical signal processing literature. Such models are mostly derived by discretizing a mathematical model, given in terms of ordinary or…

The rapid scaling of large language models (LLMs) has made low-precision training essential for reducing memory, improving efficiency, and enabling larger models and datasets. Existing convergence theories for adaptive optimizers, however,…

Machine Learning · Computer Science 2026-03-03 Xuan Tang , Jichu Li , Difan Zou

Multiplicative stochasticity such as Dropout improves the robustness and generalizability of deep neural networks. Here, we further demonstrate that always-on multiplicative stochasticity combined with simple threshold neurons are…

Machine Learning · Computer Science 2019-10-29 Georgios Detorakis , Sourav Dutta , Abhishek Khanna , Matthew Jerry , Suman Datta , Emre Neftci

Recent work in continual learning has highlighted the beneficial effect of resampling weights in the last layer of a neural network (``zapping"). Although empirical results demonstrate the effectiveness of this approach, the underlying…

Machine Learning · Computer Science 2025-07-03 Lapo Frati , Neil Traft , Jeff Clune , Nick Cheney

This work demonstrates "slimmable Neural Amp Models", whose size and computational cost can be changed without additional training and with negligible computational overhead, enabling musicians to easily trade off between the accuracy and…

Machine Learning · Computer Science 2025-11-12 Steven Atkinson

When quantizing neural networks, assigning each floating-point weight to its nearest fixed-point value is the predominant approach. We find that, perhaps surprisingly, this is not the best we can do. In this paper, we propose AdaRound, a…

Machine Learning · Computer Science 2020-07-01 Markus Nagel , Rana Ali Amjad , Mart van Baalen , Christos Louizos , Tijmen Blankevoort

Learning in artificial neural networks usually relies on continuous, externally driven weight updates, in which parameters are modified at every step in response to incoming data, error signals or reward feedback. In this setting, routine…

Neurons and Cognition · Quantitative Biology 2026-05-13 Arturo Tozzi

Deep learning algorithms demonstrate a surprising ability to learn high-dimensional tasks from limited examples. This is commonly attributed to the depth of neural networks, enabling them to build a hierarchy of abstract, low-dimensional…

Machine Learning · Computer Science 2024-07-04 Francesco Cagnetta , Leonardo Petrini , Umberto M. Tomasini , Alessandro Favero , Matthieu Wyart

We analyze the landscape and training dynamics of diagonal linear networks in a linear regression task, with the network parameters being perturbed by small isotropic normal noise. The addition of such noise may be interpreted as a…

Machine Learning · Computer Science 2025-03-18 Gabriel Clara , Sophie Langer , Johannes Schmidt-Hieber

A method of simultaneously optimizing both the structure of neural networks and the connection weights in a single training loop can reduce the enormous computational cost of neural architecture search. We focus on the probabilistic…

Neural and Evolutionary Computing · Computer Science 2022-05-27 Shota Saito , Shinichi Shirakawa

This paper investigates how the compositional structure of neural networks shapes their optimization landscape and training dynamics. We analyze the gradient flow associated with overparameterized optimization problems, which can be…

Machine Learning · Computer Science 2025-11-14 Arthur Castello Branco de Oliveira , Dhruv Jatkar , Eduardo Sontag

Descent methods for deep networks are notoriously capricious: they require careful tuning of step size, momentum and weight decay, and which method will work best on a new benchmark is a priori unclear. To address this problem, this paper…

Neural and Evolutionary Computing · Computer Science 2021-09-21 Yang Liu , Jeremy Bernstein , Markus Meister , Yisong Yue