English
Related papers

Related papers: u-$\mu$P: The Unit-Scaled Maximal Update Parametri…

200 papers

Ensembling is now recognized as an effective approach for increasing the predictive performance and calibration of deep networks. We introduce a new approach, Parameter Ensembling by Perturbation (PEP), that constructs an ensemble of…

Machine Learning · Computer Science 2020-10-27 Alireza Mehrtash , Purang Abolmaesumi , Polina Golland , Tina Kapur , Demian Wassermann , William M. Wells

The embedding-based representation learning is commonly used in deep learning recommendation models to map the raw sparse features to dense vectors. The traditional embedding manner that assigns a uniform size to all features has two…

Machine Learning · Computer Science 2021-03-12 Siyi Liu , Chen Gao , Yihong Chen , Depeng Jin , Yong Li

UMAP is a non-parametric graph-based dimensionality reduction algorithm using applied Riemannian geometry and algebraic topology to find low-dimensional embeddings of structured data. The UMAP algorithm consists of two steps: (1) Compute a…

Machine Learning · Computer Science 2021-08-31 Tim Sainburg , Leland McInnes , Timothy Q Gentner

We propose a new algorithm to learn the network of the interactions of pairwise Ising models. The algorithm is based on the pseudo-likelihood method (PLM), that has already been proven to efficiently solve the problem in a large variety of…

Disordered Systems and Neural Networks · Physics 2019-02-19 Silvio Franz , Federico Ricci-Tersenghi , Jacopo Rocchi

Image matching aims at identifying corresponding points between a pair of images. Currently, detector-free methods have shown impressive performance in challenging scenarios, thanks to their capability of generating dense matches and global…

Computer Vision and Pattern Recognition · Computer Science 2024-08-08 Xudong Cai , Yongcai Wang , Lun Luo , Minhang Wang , Deying Li , Jintao Xu , Weihao Gu , Rui Ai

A systematic mismatch exists between mathematically ideal and effective activation updates during gradient descent. As intended, parameters update in their direction of steepest descent. However, activations are argued to constitute a more…

Machine Learning · Computer Science 2026-03-11 George Bird

In speech machine learning, neural network models are typically designed by choosing an architecture with fixed layer sizes and structure. These models are then trained to maximize performance on metrics aligned with the task's objective.…

Sound · Computer Science 2026-01-22 Esteban Gómez , Tom Bäckström

Fine-tuning Large Language Models (LLMs) typically involves either full fine-tuning, which updates all model parameters, or Parameter-Efficient Fine-Tuning (PEFT), which adjusts a small subset of parameters. However, both approaches have…

Artificial Intelligence · Computer Science 2026-04-14 Shaocong Ma , Peiran Yu , Heng Huang

Fine-tuning all parameters of Large Language Models (LLMs) is computationally expensive. Parameter-Efficient Fine-Tuning (PEFT) methods address this by selectively fine-tuning specific parameters. Most of the parameter efficient fine-tuning…

Computation and Language · Computer Science 2024-11-19 Ming Dong , Kang Xue , Bolong Zheng , Tingting He

We introduce an optimization model for maximum likelihood-type estimation (M-estimation) that generalizes a large class of existing statistical models, including Huber's concomitant M-estimator, Owen's Huber/Berhu concomitant estimator, the…

Statistics Theory · Mathematics 2018-10-09 Patrick L. Combettes , Christian L. Müller

We are motivated by large scale submodular optimization problems, where standard algorithms that treat the submodular functions in the \emph{value oracle model} do not scale. In this paper, we present a model called the…

Machine Learning · Computer Science 2019-02-28 Rishabh Iyer , Jeff Bilmes

To overcome the overparameterized problem in Pre-trained Language Models (PLMs), pruning is widely used as a simple and straightforward compression method by directly removing unimportant weights. Previous first-order methods successfully…

Computation and Language · Computer Science 2023-05-18 Ting Jiang , Deqing Wang , Fuzhen Zhuang , Ruobing Xie , Feng Xia

Gradient descent and its variants are de facto standard algorithms for training machine learning models. As gradient descent is sensitive to its hyperparameters, we need to tune the hyperparameters carefully using a grid search. However,…

Machine Learning · Computer Science 2024-11-01 Yuki Takezawa , Han Bao , Ryoma Sato , Kenta Niwa , Makoto Yamada

Muon-style optimizers take a matrix-valued momentum or preconditioned update $B = U \operatorname{diag}(\sigma_1,\ldots,\sigma_r) V^\top$ and replace it with its canonical partial polar factor $\operatorname{Pol}(B) = U V^\top$. This maps…

Machine Learning · Computer Science 2026-05-27 Albert Yi

We propose subsampling as a unified algorithmic technique for submodular maximization in centralized and online settings. The idea is simple: independently sample elements from the ground set, and use simple combinatorial techniques (such…

Data Structures and Algorithms · Computer Science 2021-04-08 Christopher Harshaw , Ehsan Kazemi , Moran Feldman , Amin Karbasi

In the arena of language model fine-tuning, the traditional approaches, such as Domain-Adaptive Pretraining (DAPT) and Task-Adaptive Pretraining (TAPT), although effective, but computational intensive. This research introduces a novel…

Computation and Language · Computer Science 2024-05-10 Keyu Chen , Yuan Pang , Zi Yang

This paper proposes a novel proximal-gradient algorithm for a decentralized optimization problem with a composite objective containing smooth and non-smooth terms. Specifically, the smooth and nonsmooth terms are dealt with by gradient and…

Optimization and Control · Mathematics 2021-02-02 Zhi Li , Wei Shi , Ming Yan

Deep neural network (DNN) deployment has been confined to larger hardware devices due to their expensive computational requirements. This challenge has recently reached another scale with the emergence of large language models (LLMs). In…

Machine Learning · Computer Science 2023-08-11 Edouard Yvinec , Arnaud Dapogny , Kevin Bailly

Machine learning models are often tuned by nesting optimization of model weights inside the optimization of hyperparameters. We give a method to collapse this nested optimization into joint stochastic optimization of weights and…

Machine Learning · Computer Science 2018-03-09 Jonathan Lorraine , David Duvenaud

Extremal optimization is a new general-purpose method for approximating solutions to hard optimization problems. We study the method in detail by way of the NP-hard graph partitioning problem. We discuss the scaling behavior of extremal…

Statistical Mechanics · Physics 2009-11-07 S. Boettcher , A. G. Percus
‹ Prev 1 8 9 10 Next ›