English
Related papers

Related papers: Quantization robustness from dense representations…

200 papers

We introduce a quantization-aware training algorithm that guarantees avoiding numerical overflow when reducing the precision of accumulators during inference. We leverage weight normalization as a means of constraining parameters during…

Machine Learning · Computer Science 2023-02-01 Ian Colbert , Alessandro Pappalardo , Jakoba Petri-Koenig

Contemporary natural language processing (NLP) revolves around learning from latent document representations, generated either implicitly by neural language models or explicitly by methods such as doc2vec or similar. One of the key…

Computation and Language · Computer Science 2021-10-15 Blaž Škrlj , Matej Petkovič

Overparametrized Deep Neural Networks (DNNs) have demonstrated remarkable success in a wide variety of domains too high-dimensional for classical shallow networks subject to the curse of dimensionality. However, open questions about…

Machine Learning · Computer Science 2025-07-04 David A. Danhofer , Davide D'Ascenzo , Rafael Dubach , Tomaso Poggio

We consider the problem of training a neural network to store a set of patterns with maximal noise robustness. A solution, in terms of optimal weights and state update rules, is derived by training each individual neuron to perform either…

Neural and Evolutionary Computing · Computer Science 2024-07-24 Georgios Iatropoulos , Johanni Brea , Wulfram Gerstner

By absorbing the merits of both the model- and data-driven methods, deep physics-engaged learning scheme achieves high-accuracy and interpretable image reconstruction. It has attracted growing attention and become the mainstream for inverse…

Computer Vision and Pattern Recognition · Computer Science 2023-07-19 Bin Chen , Jiechong Song , Jingfen Xie , Jian Zhang

Low-dimensional embeddings, from classical spectral embeddings to modern neural-net-inspired methods, are a cornerstone in the modeling and analysis of complex networks. Recent work by Seshadhri et al. (PNAS 2020) suggests that such…

Machine Learning · Computer Science 2020-10-19 Sudhanshu Chanpuriya , Cameron Musco , Konstantinos Sotiropoulos , Charalampos E. Tsourakakis

We consider the optimization of deep convolutional neural networks (CNNs) such that they provide good performance while having reduced complexity if deployed on either conventional systems utilizing spatial-domain convolution or lower…

Computer Vision and Pattern Recognition · Computer Science 2018-10-30 Yoojin Choi , Mostafa El-Khamy , Jungwon Lee

We present a new framework to measure the intrinsic properties of (deep) neural networks. While we focus on convolutional networks, our framework can be extrapolated to any network architecture. In particular, we evaluate two network…

Machine Learning · Computer Science 2022-05-10 Alberto Badias , Ashis Banerjee

The increasing size of deep neural networks (DNNs) necessitates effective model compression to reduce their computational and memory footprints. Sparsity and quantization are two prominent compression methods that have been shown to reduce…

The empirical success of deep convolutional networks on tasks involving high-dimensional data such as images or audio suggests that they can efficiently approximate certain functions that are well-suited for such tasks. In this paper, we…

Machine Learning · Statistics 2022-03-22 Alberto Bietti

We demonstrate that unstructured sparsity significantly improves KV cache compression for LLMs, enabling sparsity levels up to 70% without compromising accuracy or requiring fine-tuning. We conduct a systematic exploration of pruning…

Machine Learning · Computer Science 2025-11-07 Donghyeon Joo , Helya Hosseini , Ramyad Hadidi , Bahar Asgari

Proper regularization is critical for speeding up training, improving generalization performance, and learning compact models that are cost efficient. We propose and analyze regularized gradient descent algorithms for learning shallow…

Machine Learning · Computer Science 2018-06-08 Samet Oymak

Deep neural networks have achieved human-level accuracy on almost all perceptual benchmarks. It is interesting that these advances were made using two ideas that are decades old: (a) an artificial neuron based on a linear summator and (b)…

Neural and Evolutionary Computing · Computer Science 2020-06-18 Sergey Bochkanov

When deploying deep learning models to a device, it is traditionally assumed that available computational resources (compute, memory, and power) remain static. However, real-world computing systems do not always provide stable resource…

Machine Learning · Computer Science 2021-10-11 Elvis Nunez , Maxwell Horton , Anish Prabhu , Anurag Ranjan , Ali Farhadi , Mohammad Rastegari

Continual Reinforcement Learning (CRL) is essential for developing agents that can learn, adapt, and accumulate knowledge over time. However, a fundamental challenge persists as agents must strike a delicate balance between plasticity,…

Machine Learning · Computer Science 2025-03-11 Chengqi Zheng , Haiyan Yin , Jianda Chen , Terence Ng , Yew-Soon Ong , Ivor Tsang

We show that a coherent network of lasers exhibits emergent neural computing capabilities. The proposed scheme is built on harnessing the collective behavior of laser networks for storing a number of phase patterns as stable fixed points of…

Optics · Physics 2022-04-06 Mohammad-Ali Miri , Vinod Menon

The architecture of the brain is too complex to be intuitively surveyable without the use of compressed representations that project its variation into a compact, navigable space. The task is especially challenging with high-dimensional…

Machine Learning · Computer Science 2024-07-12 James K Ruffle , Henry Watkins , Robert J Gray , Harpreet Hyare , Michel Thiebaut de Schotten , Parashkev Nachev

Learning linear combinations of multiple kernels is an appealing strategy when the right choice of features is unknown. Previous approaches to multiple kernel learning (MKL) promote sparse kernel combinations to support interpretability and…

Machine Learning · Computer Science 2010-10-28 Marius Kloft , Ulf Brefeld , Soeren Sonnenburg , Alexander Zien

We prove the first guarantees of sparse recovery for ReLU neural networks, where the sparse network weights constitute the signal to be recovered. Specifically, we study structural properties of the sparse network weights for two-layer,…

Machine Learning · Computer Science 2026-03-03 Sara Fridovich-Keil , Mert Pilanci

Krotov and Hopfield (2021) proposed a biologically plausible two-layer associative memory network with memory storage capacity exponential in the number of visible neurons. However, the capacity was only linear in the number of hidden…

Neurons and Cognition · Quantitative Biology 2026-03-11 Mohadeseh Shafiei Kafraj , Dmitry Krotov , Peter E. Latham