English
Related papers

Related papers: Sharp Capacity Thresholds in Linear Associative Me…

200 papers

Associative memories are devices storing information that can be fully retrieved given partial disclosure of it. We examine a toy model of associative memory and the ultimate limitations it is subjected to within the framework of general…

Quantum Physics · Physics 2023-11-07 Ludovico Lami , Daniel Goldwater , Gerardo Adesso

We prove that any algorithm for learning parities requires either a memory of quadratic size or an exponential number of samples. This proves a recent conjecture of Steinhardt, Valiant and Wager and shows that for some learning problems a…

Machine Learning · Computer Science 2016-02-17 Ran Raz

Memory-augmented neural networks consisting of a neural controller and an external memory have shown potentials in long-term sequential learning. Current RAM-like memory models maintain memory accessing every timesteps, thus they do not…

Machine Learning · Computer Science 2019-03-21 Hung Le , Truyen Tran , Svetha Venkatesh

In 1988, Eric B. Baum showed that two-layers neural networks with threshold activation function can perfectly memorize the binary labels of $n$ points in general position in $\mathbb{R}^d$ using only $\ulcorner n/d \urcorner$ neurons. We…

Machine Learning · Computer Science 2020-11-04 Sébastien Bubeck , Ronen Eldan , Yin Tat Lee , Dan Mikulincer

Approximate message passing (AMP) algorithms are iterative methods for signal recovery in noisy linear systems. In some scenarios, AMP algorithms need to operate within a distributed network. To address this challenge, the distributed…

Signal Processing · Electrical Eng. & Systems 2024-07-26 Jun Lu , Lei Liu , Shunqi Huang , Ning Wei , Xiaoming Chen

This work studies the (non)robustness of two-layer neural networks in various high-dimensional linearized regimes. We establish fundamental trade-offs between memorization and robustness, as measured by the Sobolev-seminorm of the model…

Machine Learning · Statistics 2021-06-07 Elvis Dohmatob

The ability of artificial agents to increment their capabilities when confronted with new data is an open challenge in artificial intelligence. The main challenge faced in such cases is catastrophic forgetting, i.e., the tendency of neural…

Machine Learning · Computer Science 2020-12-16 Eden Belouadah , Adrian Popescu , Ioannis Kanellos

We address the problem of the achievable regret rates with online logistic regression. We derive lower bounds with logarithmic regret under $L_1$, $L_2$, and $L_\infty$ constraints on the parameter values. The bounds are dominated by $d/2…

Machine Learning · Computer Science 2020-02-20 Gil I. Shamir

The rapid progress of large language models (LLMs) has laid the foundation for multimodal models. However, visual language models (VLMs) still face heavy computational costs when extended from images to videos due to high frame rates and…

Computer Vision and Pattern Recognition · Computer Science 2026-02-10 Peiran Wu , Zhuorui Yu , Yunze Liu , Chi-Hao Wu , Enmin Zhou , Junxiao Shen

The relaxed optimal $k$-thresholding pursuit (ROTP) is a recent algorithm for linear inverse problems. This algorithm is based on the optimal $k$-thresholding technique which performs vector thresholding and error metric reduction…

Information Theory · Computer Science 2024-11-14 Zhong-Feng Sun , Yun-Bin Zhao , Jin-Chuan Zhou , Zheng-Hai Huang

The storage capacity of an incremental learning algorithm for the parity machine, the Tilinglike Learning Algorithm, is analytically determined in the limit of a large number of hidden perceptrons. Different learning rules for the simple…

Disordered Systems and Neural Networks · Physics 2009-10-31 Arnaud Buhot , Mirta B. Gordon

The storage capacity of a binary classification model is the maximum number of random input-output pairs per parameter that the model can learn. It is one of the indicators of the expressive power of machine learning models and is important…

Disordered Systems and Neural Networks · Physics 2024-12-02 Sota Nishiyama , Masayuki Ohzeki

In classification problems with large output spaces (up to millions of labels), the last layer can require an enormous amount of memory. Using sparse connectivity would drastically reduce the memory requirements, but as we show below, it…

Machine Learning · Computer Science 2023-11-08 Erik Schultheis , Rohit Babbar

Finding a small spectral approximation for a tall $n \times d$ matrix $A$ is a fundamental numerical primitive. For a number of reasons, one often seeks an approximation whose rows are sampled from those of $A$. Row sampling improves…

Data Structures and Algorithms · Computer Science 2016-04-20 Michael B. Cohen , Cameron Musco , Jakub Pachocki

Associative memory models, in theoretical neuro- and computer sciences, can generally store a sublinear number of memories. We show that using quantum annealing for recall tasks endows associative memory models with exponential storage…

Quantum Physics · Physics 2018-01-03 Siddhartha Santra , Omar Shehab , Radhakrishnan Balu

Recent LLMs have hundreds of billions of parameters consuming vast resources. Furthermore, the so called "AI scaling law" for transformers suggests that the number of parameters must scale linearly with the size of the data. In response, we…

Computation and Language · Computer Science 2026-01-05 B. N. Kausik

An active learner is given a class of models, a large set of unlabeled examples, and the ability to interactively query labels of a subset of these examples; the goal of the learner is to learn a model in the class that fits the data well.…

Machine Learning · Computer Science 2015-06-09 Kamalika Chaudhuri , Sham Kakade , Praneeth Netrapalli , Sujay Sanghavi

The ultimate goal of a supervised learning algorithm is to produce models constructed on the training data that can generalize well to new examples. In classification, functional margin maximization -- correctly classifying as many training…

Machine Learning · Computer Science 2020-01-29 Nikolaos Nikolaou , Henry Reeve , Gavin Brown

When rows of an $n \times d$ matrix $A$ are given in a stream, we study algorithms for approximating the top eigenvector of the matrix ${A}^TA$ (equivalently, the top right singular vector of $A$). We consider worst case inputs $A$ but…

Data Structures and Algorithms · Computer Science 2024-12-17 Praneeth Kacham , David P. Woodruff

We consider the problem of sampling from a strongly log-concave density in $\mathbb{R}^d$, and prove an information theoretic lower bound on the number of stochastic gradient queries of the log density needed. Several popular sampling…

Machine Learning · Statistics 2021-07-06 Niladri S. Chatterji , Peter L. Bartlett , Philip M. Long
‹ Prev 1 3 4 5 6 7 10 Next ›