English
Related papers

Related papers: Exponentially Increasing the Capacity-to-Computati…

200 papers

Modularity has been widely studied as a mechanism to improve the capabilities of neural networks through various techniques such as hand-crafted modular architectures and automatic approaches. While these methods have sometimes shown…

Neural and Evolutionary Computing · Computer Science 2024-10-28 Humphrey Munn , Marcus Gallagher

Analyses of accelerated (momentum-based) gradient descent usually assume bounded condition number to obtain exponential convergence rates. However, in many real problems, e.g., kernel methods or deep neural networks, the condition number,…

Machine Learning · Computer Science 2018-03-06 Chaoyue Liu , Mikhail Belkin

We consider the problem of estimating an upper bound on the capacity of a memoryless channel with unknown channel law and continuous output alphabet. A novel data-driven algorithm is proposed that exploits the dual representation of…

Information Theory · Computer Science 2024-01-25 Christian Häger , Erik Agrell

We consider multi-class classification where the predictor has a hierarchical structure that allows for a very large number of labels both at train and test time. The predictive power of such models can heavily depend on the structure of…

Machine Learning · Statistics 2017-03-06 Yacine Jernite , Anna Choromanska , David Sontag

In this paper we consider the possibility of computing rather than training the decision layer weights of a neural classifier. Such a possibility arises in two way, from making an appropriate choice of loss function and by solving a problem…

Machine Learning · Computer Science 2022-09-21 Eugene Wong

The recently introduced graph parameter tree-cut width plays a similar role with respect to immersions as the graph parameter treewidth plays with respect to minors. In this paper, we provide the first algorithmic applications of tree-cut…

Data Structures and Algorithms · Computer Science 2022-06-03 Robert Ganian , Eun Jung Kim , Stefan Szeider

The learnability of different neural architectures can be characterized directly by computable measures of data complexity. In this paper, we reframe the problem of architecture selection as understanding how data determines the most…

Machine Learning · Computer Science 2018-02-14 William H. Guss , Ruslan Salakhutdinov

Kernel conditional mean embeddings (CMEs) offer a powerful framework for representing conditional distribution, but they often face scalability and expressiveness challenges. In this work, we propose a new method that effectively combines…

Machine Learning · Statistics 2024-03-19 Eiki Shimizu , Kenji Fukumizu , Dino Sejdinovic

Weight-sharing plays a significant role in the success of many deep neural networks, by increasing memory efficiency and incorporating useful inductive priors about the problem into the network. But understanding how weight-sharing can be…

Machine Learning · Computer Science 2023-12-15 Oscar Chang , Hod Lipson

In order to speed-up classification models when facing a large number of categories, one usual approach consists in organizing the categories in a particular structure, this structure being then used as a way to speed-up the prediction…

Machine Learning · Computer Science 2015-11-26 Aurélia Léon , Ludovic Denoyer

Latent variable models are an elegant framework for capturing rich probabilistic dependencies in many applications. However, current approaches typically parametrize these models using conditional probability tables, and learning relies…

Machine Learning · Computer Science 2012-10-19 Ankur P. Parikh , Le Song , Mariya Ishteva , Gabi Teodoru , Eric P. Xing

Algorithms typically come with tunable parameters that have a considerable impact on the computational resources they consume. Too often, practitioners must hand-tune the parameters, a tedious and error-prone task. A recent line of research…

Machine Learning · Computer Science 2020-11-24 Maria-Florina Balcan , Tuomas Sandholm , Ellen Vitercik

Single layer feedforward networks with random weights are successful in a variety of classification and regression problems. These networks are known for their non-iterative and fast training algorithms. A major drawback of these networks…

Neural and Evolutionary Computing · Computer Science 2020-09-25 Ajay M. Patrikar

Convolutional Neural Networks experience catastrophic forgetting when optimized on a sequence of learning problems: as they meet the objective of the current training examples, their performance on previous tasks drops drastically. In this…

Computer Vision and Pattern Recognition · Computer Science 2020-04-02 Davide Abati , Jakub Tomczak , Tijmen Blankevoort , Simone Calderara , Rita Cucchiara , Babak Ehteshami Bejnordi

Quantization is a widely used compression method that effectively reduces redundancies in over-parameterized neural networks. However, existing quantization techniques for deep neural networks often lack a comprehensive error analysis due…

Machine Learning · Computer Science 2023-09-21 Jinjie Zhang , Rayan Saab

We propose Partition Tree, a novel tree-based framework for conditional density estimation over general outcome spaces that supports both continuous and categorical variables within a unified formulation. Our approach models conditional…

Machine Learning · Computer Science 2026-05-13 Felipe Angelim , Alessandro Leite

We propose conditioning field initialization for neural network based topology optimization. In this work, we focus on (1) improving upon existing neural network based topology optimization, (2) demonstrating that by using a prior initial…

Machine Learning · Computer Science 2023-05-19 Hongrui Chen , Aditya Joglekar , Levent Burak Kara

A key challenge in designing convolutional network models is sizing them appropriately. Many factors are involved in these decisions, including number of layers, feature maps, kernel sizes, etc. Complicating this further is the fact that…

Machine Learning · Computer Science 2014-02-20 David Eigen , Jason Rolfe , Rob Fergus , Yann LeCun

A difficult task in modeling with Bayesian networks is the elicitation of numerical parameters of Bayesian networks. A large number of parameters is needed to specify a conditional probability table (CPT) that has a larger parent set. In…

Artificial Intelligence · Computer Science 2016-08-10 Jiří Vomlel , Petr Tichavský

Training neural networks requires significant computational resources and energy. Methods like mixed-precision and quantization-aware training reduce bit usage, yet they still depend heavily on computationally expensive gradient-based…

Machine Learning · Computer Science 2025-09-30 Noa Cohen , Omkar Joglekar , Dotan Di Castro , Vladimir Tchuiev , Shir Kozlovsky , Michal Moshkovitz
‹ Prev 1 8 9 10 Next ›