English
Related papers

Related papers: Why Zeroth-Order Adaptation May Forget Less: A Ran…

200 papers

We propose RSO (random search optimization), a gradient free Markov Chain Monte Carlo search based approach for training deep neural networks. To this end, RSO adds a perturbation to a weight in a deep neural network and tests if it reduces…

Machine Learning · Computer Science 2020-05-13 Rohun Tripathi , Bharat Singh

The study of first-order optimization algorithms (FOA) typically starts with assumptions on the objective functions, most commonly smoothness and strong convexity. These metrics are used to tune the hyperparameters of FOA. We introduce a…

Machine Learning · Computer Science 2024-05-30 Charles Guille-Escuret , Baptiste Goujaud , Manuela Girotti , Ioannis Mitliagkas

The intrinsic capability to continuously learn a changing data stream is a desideratum of deep neural networks (DNNs). However, current DNNs suffer from catastrophic forgetting, which interferes with remembering past knowledge. To mitigate…

Machine Learning · Computer Science 2026-02-03 Nghia D. Nguyen , Hieu Trung Nguyen , Ang Li , Hoang Pham , Viet Anh Nguyen , Khoa D. Doan

We present a novel adaptive optimization algorithm for large-scale machine learning problems. Equipped with a low-cost estimate of local curvature and Lipschitz smoothness, our method dynamically adapts the search direction and step-size.…

Machine Learning · Computer Science 2021-09-14 Majid Jahani , Sergey Rusakov , Zheng Shi , Peter Richtárik , Michael W. Mahoney , Martin Takáč

Surface reconstruction with preservation of geometric features is a challenging computer vision task. Despite significant progress in implicit shape reconstruction, state-of-the-art mesh extraction methods often produce aliased,…

Computer Vision and Pattern Recognition · Computer Science 2023-12-01 Natalia Soboleva , Olga Gorbunova , Maria Ivanova , Evgeny Burnaev , Matthias Nießner , Denis Zorin , Alexey Artemov

The analysis of gradient descent-type methods typically relies on the Lipschitz continuity of the objective gradient. This generally requires an expensive hyperparameter tuning process to appropriately calibrate a stepsize for a given…

Optimization and Control · Mathematics 2023-11-16 Albert S. Berahas , Lindon Roberts , Fred Roosta

Deep learning models, despite their impressive achievements, suffer from high computational costs and memory requirements, limiting their usability in resource-constrained environments. Sparse neural networks significantly alleviate these…

Machine Learning · Computer Science 2026-03-16 Jie Ji , Gen Li , Kaiyuan Deng , Fatemeh Afghah , Xiaolong Ma

Retrieval systems rely on representations learned by increasingly powerful models. However, due to the high training cost and inconsistencies in learned representations, there is significant interest in facilitating communication between…

Machine Learning · Computer Science 2026-05-20 Simone Ricci , Niccolò Biondi , Federico Pernici , Ioannis Patras , Alberto Del Bimbo

Deep neural networks are easily fooled by small perturbations known as adversarial attacks. Adversarial Training (AT) is a technique aimed at learning features robust to such attacks and is widely regarded as a very effective defense.…

Machine Learning · Computer Science 2020-09-11 Theodoros Tsiligkaridis , Jay Roberts

Most successful stochastic black-box optimizers, such as CMA-ES, use rankings of the individual samples to obtain a new search distribution. Yet, the use of rankings also introduces several issues such as the underlying optimization…

Machine Learning · Statistics 2022-06-14 Maximilian Hüttenrauch , Gerhard Neumann

Zeroth-order (ZO) optimization has long been favored for its biological plausibility and its capacity to handle non-differentiable objectives, yet its computational complexity has historically limited its application in deep neural…

Machine Learning · Computer Science 2026-02-12 Sansheng Cao , Zhengyu Ma , Yonghong Tian

A core component of the recent success of self-supervised learning is cropping data augmentation, which selects sub-regions of an image to be used as positive views in the self-supervised loss. The underlying assumption is that randomly…

Computer Vision and Pattern Recognition · Computer Science 2023-04-10 Shlok Mishra , Anshul Shah , Ankan Bansal , Abhyuday Jagannatha , Janit Anjaria , Abhishek Sharma , David Jacobs , Dilip Krishnan

Large language models are commonly trained through multi-stage post-training: first via RLHF, then fine-tuned for other downstream objectives. Yet even small downstream updates can compromise earlier learned behaviors (e.g., safety),…

Machine Learning · Computer Science 2026-05-13 Mahdi Sabbaghi , George Pappas , Adel Javanmard , Hamed Hassani

Quantization is an effective technique to reduce memory footprint, inference latency, and power consumption of deep learning models. However, existing quantization methods suffer from accuracy degradation compared to full-precision (FP)…

Machine Learning · Computer Science 2022-10-14 Zheng Wang , Juncheng B Li , Shuhui Qu , Florian Metze , Emma Strubell

First-order optimization (FOO) algorithms are pivotal in numerous computational domains such as machine learning and signal denoising. However, their application to complex tasks like neural network training often entails significant…

Machine Learning · Computer Science 2024-10-30 Yao Shu , Jiongfeng Fang , Ying Tiffany He , Fei Richard Yu

Loss of trainability refers to a phenomenon in continual learning where parameter updates no longer make progress on the optimization objective, so accuracy stalls or degrades as the learning problem changes over time. In this paper, we…

Machine Learning · Computer Science 2025-12-11 Gunbir Singh Baveja , Alex Lewandowski , Mark Schmidt

Bayesian Optimization (BO) is a popular approach to optimizing expensive-to-evaluate black-box functions. Despite the success of BO, its performance may decrease exponentially as the dimensionality increases. A common framework to tackle…

Machine Learning · Computer Science 2024-12-24 Quoc-Anh Hoang Nguyen , The Hung Tran

This paper is concerned with parameter identification problem for finite impulse response (FIR) systems with binary-valued observations under low computational complexity. Most of the existing algorithms under binary-valued observations…

Systems and Control · Electrical Eng. & Systems 2024-12-09 Tianning Han , Ying Wang , Yanlong Zhao

Variants dropout methods have been designed for the fully-connected layer, convolutional layer and recurrent layer in neural networks, and shown to be effective to avoid overfitting. As an appealing alternative to recurrent and…

Computation and Language · Computer Science 2019-07-29 Lin Zehui , Pengfei Liu , Luyao Huang , Junkun Chen , Xipeng Qiu , Xuanjing Huang

In this paper, we propose and analyze zeroth-order stochastic approximation algorithms for nonconvex and convex optimization, with a focus on addressing constrained optimization, high-dimensional setting and saddle-point avoiding. To handle…

Optimization and Control · Mathematics 2019-01-16 Krishnakumar Balasubramanian , Saeed Ghadimi