English
Related papers

Related papers: Sign Lock-In: Randomly Initialized Weight Signs Pe…

200 papers

Contrastive Language-Image Pre-training (CLIP) has achieved widely applications in various computer vision tasks, e.g., text-to-image generation, Image-Text retrieval and Image captioning. However, CLIP suffers from high memory and…

Computer Vision and Pattern Recognition · Computer Science 2026-02-06 Kangjie Zhang , Wenxuan Huang , Xin Zhou , Boxiang Zhou , Dejia Song , Yuan Xie , Baochang Zhang , Lizhuang Ma , Nemo Chen , Xu Tang , Yao Hu , Shaohui Lin

Based on $\alpha$-stable random projections with small $\alpha$, we develop a simple algorithm for compressed sensing (sparse signal recovery) by utilizing only the signs (i.e., 1-bit) of the measurements. Using only 1-bit information of…

Methodology · Statistics 2015-11-12 Ping Li

Current Large Language Models (LLMs) face three major challenges: context length limitations, high inference costs, and catastrophic forgetting during continual learning. While Mixture-of-Experts (MoE) architectures mitigate some of these…

Machine Learning · Computer Science 2025-12-23 Zhongpan Tang

The application of loss reweighting in modern deep learning presents a nuanced picture. While it fails to alter the terminal learning phase in overparameterized deep neural networks (DNNs) trained on high-dimensional datasets, empirical…

Machine Learning · Computer Science 2026-01-21 Yize Zhao , Christos Thrampoulidis

The deployment of large language models (LLMs) is frequently hindered by prohibitive memory and computational requirements. While quantization mitigates these bottlenecks, maintaining model fidelity in the sub-1-bit regime remains a…

Machine Learning · Computer Science 2026-02-06 Banseok Lee , Dongkyu Kim , Youngcheon You , Youngmin Kim

High energy particles from cosmic rays or packaging materials can generate a glitch or a current transient (single event transient or SET) in a logic circuit. This SET can eventually get captured in a register resulting in a flip of the…

Hardware Architecture · Computer Science 2017-06-16 Nanditha P. Rao , Madhav P. Desai

The minimal norm weight perturbations of DNNs required to achieve a specified change in output are derived and the factors determining its size are discussed. These single-layer exact formulae are contrasted with more generic multi-layer…

Machine Learning · Computer Science 2026-05-19 Bethan Evans , Jared Tanner

It has recently been shown that a suitably interconnected network of tunable telegraphic noise generators or "p-bits" can be used to perform even precise arithmetic functions like a 32-bit adder. In this paper we use simulations based on…

Mesoscale and Nanoscale Physics · Physics 2017-04-13 Rafatul Faria , Kerem Yunus Camsari , Supriyo Datta

Large Language Models (LLMs) have demonstrated exceptional proficiency in language-related tasks, but their deployment poses significant challenges due to substantial memory and storage requirements. Weight-only quantization has emerged as…

Computation and Language · Computer Science 2024-10-10 Wenhua Cheng , Weiwei Zhang , Haihao Shen , Yiyang Cai , Xin He , Kaokao Lv , Yi Liu

Binary neural networks (BNNs) have attracted broad research interest due to their efficient storage and computational ability. Nevertheless, a significant challenge of BNNs lies in handling discrete constraints while ensuring bit entropy…

Computer Vision and Pattern Recognition · Computer Science 2022-10-05 Mingbao Lin , Rongrong Ji , Zihan Xu , Baochang Zhang , Fei Chao , Chia-Wen Lin , Ling Shao

We describe a simple and general neural network weight compression approach, in which the network parameters (weights and biases) are represented in a "latent" space, amounting to a reparameterization. This space is equipped with a learned…

Machine Learning · Computer Science 2020-02-18 Deniz Oktay , Johannes Ballé , Saurabh Singh , Abhinav Shrivastava

Complex systems can be effectively modeled via graphs that encode networked interactions, where relations between entities or nodes are often quantified by signed edge weights, e.g., promotion/inhibition in gene regulatory networks, or…

Optimization and Control · Mathematics 2024-04-05 Anqi Dong , Can Chen , Tryphon T. Georgiou

We investigate how the computational difficulty of contracting tensor networks depends on the sign structure of the tensor entries. Using results from computational complexity, we observe that the approximate contraction of tensor networks…

Quantum Physics · Physics 2025-01-22 Jielun Chen , Jiaqing Jiang , Dominik Hangleiter , Norbert Schuch

The performance gap between training sparse neural networks from scratch (PaI) and dense-to-sparse training presents a major roadblock for efficient deep learning. According to the Lottery Ticket Hypothesis, PaI hinges on finding a problem…

Machine Learning · Computer Science 2025-10-24 Advait Gadhikar , Tom Jacobs , Chao Zhou , Rebekka Burkholz

We identify the Spectral Energy Gain in extreme model compression, where low-rank binary approximations outperform tiny-rank floating-point baselines for heavy-tailed spectra. However, prior attempts fail to realize this potential, trailing…

Machine Learning · Computer Science 2026-05-05 Banseok Lee , Youngmin Kim

Continuous neural representations have recently emerged as a powerful and flexible alternative to classical discretized representations of signals. However, training them to capture fine details in multi-scale signals is difficult and…

Machine Learning · Computer Science 2022-10-06 Sifan Wang , Hanwen Wang , Jacob H. Seidman , Paris Perdikaris

By introducing sign constraints on the weights, this paper proposes sign constrained rectifier networks (SCRNs), whose training can be solved efficiently by the well known majorization-minimization (MM) algorithms. We prove that the…

Machine Learning · Computer Science 2017-11-16 Senjian An , Farid Boussaid , Mohammed Bennamoun , Ferdous Sohel

Inductive one-bit matrix completion is motivated by modern applications such as recommender systems, where new users would appear at test stage with the ratings consisting of only ones and no zeros. We propose a unified graph signal…

Machine Learning · Computer Science 2023-02-09 Chao Chen , Haoyu Geng , Gang Zeng , Zhaobing Han , Hua Chai , Xiaokang Yang , Junchi Yan

Autoencoders are a prominent model in many empirical branches of machine learning and lossy data compression. However, basic theoretical questions remain unanswered even in a shallow two-layer setting. In particular, to what degree does a…

Machine Learning · Computer Science 2024-02-08 Kevin Kögler , Alexander Shevchenko , Hamed Hassani , Marco Mondelli

In 1-bit compressed sensing, the aim is to estimate a $k$-sparse unit vector $x\in S^{n-1}$ within an $\epsilon$ error (in $\ell_2$) from minimal number of linear measurements that are quantized to just their signs, i.e., from measurements…

Information Theory · Computer Science 2023-10-13 Namiko Matsumoto , Arya Mazumdar