English
Related papers

Related papers: A theory of capacity and sparse neural encoding

200 papers

Sensory processing is hard because the variables of interest are encoded in spike trains in a relatively complex way. A major goal in sensory processing is to understand how the brain extracts those variables. Here we revisit a common…

Neurons and Cognition · Quantitative Biology 2017-09-06 Sina Tootoonian , Peter Latham

Sparsity has become popular in machine learning, because it can save computational resources, facilitate interpretations, and prevent overfitting. In this paper, we discuss sparsity in the framework of neural networks. In particular, we…

Machine Learning · Computer Science 2020-06-30 Mohamed Hebiri , Johannes Lederer

Lattice field theories are fundamental testbeds for computational physics; yet, sampling their Boltzmann distributions remains challenging due to multimodality and long-range correlations. While normalizing flows offer a promising…

Machine Learning · Computer Science 2025-10-16 Andrey Bryutkin , Youssef Marzouk

We recently proved threshold saturation for spatially coupled sparse superposition codes on the additive white Gaussian noise channel. Here we generalize our analysis to a much broader setting. We show for any memoryless channel that…

Information Theory · Computer Science 2016-03-16 Jean Barbier , Mohamad Dia , Nicolas Macris

The key-value (KV) cache in the tensor version of transformers presents a significant bottleneck during inference. While previous work analyzes the fundamental space complexity barriers in standard attention mechanisms [Haris and Onak,…

Machine Learning · Computer Science 2025-03-28 Yifang Chen , Xiaoyu Li , Yingyu Liang , Zhenmei Shi , Zhao Song , Yu Tian

Transformers are powerful sequence models, but require time and memory that grows quadratically with the sequence length. In this paper we introduce sparse factorizations of the attention matrix which reduce this to $O(n \sqrt{n})$. We also…

Machine Learning · Computer Science 2019-04-25 Rewon Child , Scott Gray , Alec Radford , Ilya Sutskever

The brain is a noisy system subject to energy constraints. These facts are rarely taken into account when modelling artificial neural networks. In this paper, we are interested in demonstrating that those factors can actually lead to the…

Neural and Evolutionary Computing · Computer Science 2017-09-26 Eliott Coyac , Vincent Gripon , Charlotte Langlais , Claude Berrou

Reinforcement learning under partial observability requires deciding what information to retain, yet most memory-based approaches do not explicitly model short-term-to-long-term transfer of symbolic observations. We study this transfer…

Machine Learning · Computer Science 2026-05-22 Taewoon Kim , Vincent François-Lavet , Michael Cochez

Although modern deep learning often relies on massive over-parameterized models, the fundamental interplay between capacity, sparsity, and robustness in low-capacity networks remains a vital area of study. We introduce a controlled…

Machine Learning · Computer Science 2025-07-23 Yash Kumar

Neural networks with synaptic weights constructed according to the weighted Hebb rule, a variant of the familiar Hebb rule, are studied in the presence of noise(finite temperature), when the number of stored patterns is finite and in the…

Condensed Matter · Physics 2009-10-22 Caren Marzban , Raju Viswanathan

Both PAC-Bayesian and Sample Compress learning frameworks are instrumental for deriving tight (non-vacuous) generalization bounds for neural networks. We leverage these results in a meta-learning scheme, relying on a hypernetwork that…

Machine Learning · Computer Science 2025-06-06 Benjamin Leblanc , Mathieu Bazinet , Nathaniel D'Amours , Alexandre Drouin , Pascal Germain

We investigate the difficulties of training sparse neural networks and make new observations about optimization dynamics and the energy landscape within the sparse regime. Recent work of \citep{Gale2019, Liu2018} has shown that sparse…

Machine Learning · Computer Science 2020-10-08 Utku Evci , Fabian Pedregosa , Aidan Gomez , Erich Elsen

Sparse deep learning aims to address the challenge of huge storage consumption by deep neural networks, and to recover the sparse structure of target functions. Although tremendous empirical successes have been achieved, most sparse deep…

Machine Learning · Statistics 2020-11-17 Jincheng Bai , Qifan Song , Guang Cheng

Real-world processes often contain intermediate state that can be modeled as an extremely sparse activation tensor. In this work, we analyze the identifiability of such sparse and local latent intermediate variables, which we call motifs.…

Machine Learning · Computer Science 2026-03-04 Kavi Gupta , Osbert Bastani , Armando Solar-Lezama

Recent work on the lottery ticket hypothesis has produced highly sparse Transformers for NMT while maintaining BLEU. However, it is unclear how such pruning techniques affect a model's learned representations. By probing Transformers with…

Computation and Language · Computer Science 2020-10-14 Rajiv Movva , Jason Y. Zhao

Sparsity is a desirable attribute. It can lead to more efficient and more effective representations compared to the dense model. Meanwhile, learning sparse latent representations has been a challenging problem in the field of computer…

Computer Vision and Pattern Recognition · Computer Science 2022-09-22 Hanao Li , Tian Han

The sparsity of Deep Neural Networks is well investigated to maximize the performance and reduce the size of overparameterized networks as possible. Existing methods focus on pruning parameters in the training process by using thresholds…

Machine Learning · Computer Science 2023-07-17 Mingjian Ni , Guangyao Chen , Xiawu Zheng , Peixi Peng , Li Yuan , Yonghong Tian

In the present paper, we analyze symmetric mixed states corresponding to the so-called concept formation on a sparsely encoded associative memory model with 0-1 neurons. Three types of mixed states, OR, AND and a majority decision mixed…

Disordered Systems and Neural Networks · Physics 2007-05-23 Tomoyuki Kimoto , Masato Okada

Inducing sparseness while training neural networks has been shown to yield models with a lower memory footprint but similar effectiveness to dense models. However, sparseness is typically induced starting from a dense model, and thus this…

Machine Learning · Computer Science 2022-03-30 Thomas Demeester , Johannes Deleu , Fréderic Godin , Chris Develder

The success of deep learning in high-dimensional settings is often attributed to the presence of low-dimensional structure in real-world data. While standard theoretical models typically assume that this structure lies in the target…

Machine Learning · Computer Science 2026-05-15 Elisabetta Cornacchia , Laurent Massoulié