English
Related papers

Related papers: Hyperparameter Tuning is All You Need for LISTA

200 papers

Iterative refinement is particularly popular for numerical solution of linear systems of equations. We extend it to Low Rank Approximation of a matrix (LRA) and observe close link of the resulting algorithm to oversampling techniques,…

Numerical Analysis · Mathematics 2024-11-28 Victor Y. Pan , Qi Luan , Soo Go

A recent line of work has shown that an overparametrized neural network can perfectly fit the training data, an otherwise often intractable nonconvex optimization problem. For (fully-connected) shallow networks, in the best case scenario,…

Machine Learning · Computer Science 2019-10-30 Armin Eftekhari , ChaeHwan Song , Volkan Cevher

Many modern neural network architectures are trained in an overparameterized regime where the parameters of the model exceed the size of the training dataset. Sufficiently overparameterized neural network architectures in principle have the…

Machine Learning · Computer Science 2019-02-14 Samet Oymak , Mahdi Soltanolkotabi

Parameter Efficient Tuning has been an prominent approach to adapt the Large Language Model to downstream tasks. Most previous works considers adding the dense trainable parameters, where all parameters are used to adapt certain task. We…

Computation and Language · Computer Science 2023-11-16 Yun Zhu , Nevan Wichers , Chu-Cheng Lin , Xinyi Wang , Tianlong Chen , Lei Shu , Han Lu , Canoee Liu , Liangchen Luo , Jindong Chen , Lei Meng

This paper proposes the first-ever algorithmic framework for tuning hyper-parameters of stochastic optimization algorithm based on reinforcement learning. Hyper-parameters impose significant influences on the performance of stochastic…

Machine Learning · Computer Science 2020-03-11 Haotian Zhang , Jianyong Sun , Zongben Xu

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

Training large models ranging from millions to billions of parameters is highly resource-intensive, requiring significant time, compute, and memory. It is observed that most of the learning (higher change in weights) takes place in the…

Machine Learning · Computer Science 2026-03-16 Krishu K Thapa , Reet Barik , Krishna Teja Chitty-Venkata , Murali Emani , Venkatram Vishwanath

We demonstrate the possibility of what we call sparse learning: accelerated training of deep neural networks that maintain sparse weights throughout training while achieving dense performance levels. We accomplish this by developing sparse…

Machine Learning · Computer Science 2019-08-27 Tim Dettmers , Luke Zettlemoyer

We introduce a novel optimization algorithm for image recovery under learned sparse and low-rank constraints, which we parameterize as weighted extensions of the $\ell_p^p$-vector and $\mathcal S_p^p$ Schatten-matrix quasi-norms for…

Computer Vision and Pattern Recognition · Computer Science 2023-04-21 Stamatios Lefkimmiatis , Iaroslav Koshelev

A matrix algorithm runs superfast (aka at sublinear cost) if it involves much fewer flops and memory cells than an input matrix has entries. Big Data are frequently represented by matrices of immense sizes that cannot be handled directly…

Numerical Analysis · Mathematics 2025-11-11 Qi Luan , Victor Y. Pan

Sherpa is a hyperparameter optimization library for machine learning models. It is specifically designed for problems with computationally expensive, iterative function evaluations, such as the hyperparameter tuning of deep neural networks.…

Machine Learning · Computer Science 2020-05-11 Lars Hertel , Julian Collado , Peter Sadowski , Jordan Ott , Pierre Baldi

Convex-composite optimization, which minimizes an objective function represented by the sum of a differentiable function and a convex one, is widely used in machine learning and signal/image processing. Fast Iterative Shrinkage Thresholding…

Optimization and Control · Mathematics 2022-05-12 Hiroki Tanabe , Ellen H. Fukuda , Nobuo Yamashita

LoRA is a technique that reduces the number of trainable parameters in a neural network by introducing low-rank adapters to linear layers. This technique is used both for fine-tuning and full training of large language models. This paper…

Machine Learning · Computer Science 2024-06-17 Daria Cherniuk , Aleksandr Mikhalev , Ivan Oseledets

Recurrent neural networks (RNNs) are powerful and effective for processing sequential data. However, RNNs are usually considered "black box" models whose internal structure and learned parameters are not interpretable. In this paper, we…

Machine Learning · Statistics 2016-11-23 Scott Wisdom , Thomas Powers , James Pitton , Les Atlas

Single-snapshot direction-of-arrival (DOA) estimation using sparse linear arrays (SLAs) has gained significant attention in the field of automotive MIMO radars. This is due to the dynamic nature of automotive settings, where multiple…

Signal Processing · Electrical Eng. & Systems 2023-09-18 Yunqiao Hu , Shunqiao Sun

The Lottery Ticket Hypothesis (LTH) suggests that over-parameterized neural networks contain sparse subnetworks ("winning tickets") capable of matching full model performance when trained from scratch. With the growing reliance on…

Machine Learning · Computer Science 2025-12-30 Hamed Damirchi , Cristian Rodriguez-Opazo , Ehsan Abbasnejad , Zhen Zhang , Javen Shi

We introduce a machine-learning framework to learn the hyperparameter sequence of first-order methods (e.g., the step sizes in gradient descent) to quickly solve parametric convex optimization problems. Our computational architecture…

Optimization and Control · Mathematics 2024-12-23 Rajiv Sambharya , Bartolomeo Stellato

A new supervised learning algorithm, SNN/LP, is proposed for Spiking Neural Networks. This novel algorithm uses limited precision for both synaptic weights and synaptic delays; 3 bits in each case. Also a genetic algorithm is used for the…

Neural and Evolutionary Computing · Computer Science 2014-07-02 Evangelos Stromatias , John Marsland

Neural networks have seen limited use in prediction for high-dimensional data with small sample sizes, because they tend to overfit and require tuning many more hyperparameters than existing off-the-shelf machine learning methods. With…

Machine Learning · Statistics 2020-05-12 Jean Feng , Noah Simon

We consider the iterative shrinkage/thresholding algorithm (ISTA) applied to a cost function composed of a data fidelity term and a penalty term. The penalty is non-convex but the concavity of the penalty is accounted for by the data…

Optimization and Control · Mathematics 2016-04-20 Ilker Bayram