English
Related papers

Related papers: Template-Based Posit Multiplication for Training a…

200 papers

Although not primarily designed for this purpose, floating-point numbers are often used to represent integral values, with some applications explicitly relying on this capability. However, the integral representation properties of IEEE 754…

Hardware Architecture · Computer Science 2025-12-01 Laslo Hunhold

Linear recurrent models offer linear-time sequence processing but often suffer from suboptimal long-range memory. We trace this to the decay spectrum: for $N$ channels, random initialization collapses the minimum spectral gap to…

Machine Learning · Computer Science 2026-04-10 Yang Cao

We introduce PatternBoost, a flexible method for finding interesting constructions in mathematics. Our algorithm alternates between two phases. In the first ``local'' phase, a classical search algorithm is used to produce many desirable…

Combinatorics · Mathematics 2024-11-04 François Charton , Jordan S. Ellenberg , Adam Zsolt Wagner , Geordie Williamson

Number theoretic transform (NTT) is the most efficient method for multiplying two polynomials of high degree with integer coefficients, due to its series of advantages in terms of algorithm and implementation, and is consequently…

Cryptography and Security · Computer Science 2022-11-28 Zhichuang Liang , Yunlei Zhao

A class of two-bit bit flipping algorithms for decoding low-density parity-check codes over the binary symmetric channel was proposed in [1]. Initial results showed that decoders which employ a group of these algorithms operating in…

Information Theory · Computer Science 2012-05-22 Dung Viet Nguyen , Bane Vasic , Michael W. Marcellin

On modern architectures, the performance of 32-bit operations is often at least twice as fast as the performance of 64-bit operations. By using a combination of 32-bit and 64-bit floating point arithmetic, the performance of many dense and…

Mathematical Software · Computer Science 2015-05-13 Marc Baboulin , Alfredo Buttari , Jack Dongarra , Jakub Kurzak , Julie Langou , Julien Langou , Piotr Luszczek , Stanimire Tomov

In some studies \citep[e.g.,][]{zhang2016understanding} of deep learning, it is observed that over-parametrized deep neural networks achieve a small testing error even when the training error is almost zero. Despite numerous works towards…

Machine Learning · Statistics 2022-02-25 Yue Xing , Qifan Song , Guang Cheng

The computation of select eigenvalues and eigenvectors of large, sparse matrices is fundamental to a wide range of applications. Accordingly, evaluating the numerical performance of emerging alternatives to the IEEE 754 floating-point…

Numerical Analysis · Mathematics 2025-11-27 Laslo Hunhold , James Quinlan , Stefan Wesner

In this paper, we design fixed-parameter tractable (FPT) algorithms for (non-monotone) submodular maximization subject to a matroid constraint, where the matroid rank $r$ is treated as a fixed parameter that is independent of the total…

Data Structures and Algorithms · Computer Science 2025-09-03 Shamisa Nematollahi , Adrian Vladu , Junyao Zhao

Physics-informed neural networks solve partial differential equations by training neural networks. Since this method approximates infinite-dimensional PDE solutions with finite collocation points, minimizing discretization errors by…

Machine Learning · Computer Science 2024-12-11 Takashi Matsubara , Takaharu Yaguchi

We have designed a new symbolic-numeric strategy to compute efficiently and accurately floating point Puiseux series defined by a bivariate polynomial over an algebraic number field. In essence, computations modulo a well chosen prime $p$…

Symbolic Computation · Computer Science 2008-03-21 Adrien Poteaux , Marc Rybowicz

Iterative refinement -- start with a random guess, then iteratively improve the guess -- is a useful paradigm for representation learning because it offers a way to break symmetries among equally plausible explanations for the data. This…

Machine Learning · Computer Science 2023-01-03 Michael Chang , Thomas L. Griffiths , Sergey Levine

In training neural networks, it is common practice to use partial gradients computed over batches, mostly very small subsets of the training set. This approach is motivated by the argument that such a partial gradient is close to the true…

Machine Learning · Computer Science 2024-11-25 Jan Spörer , Bernhard Bermeitinger , Tomas Hrycej , Niklas Limacher , Siegfried Handschuh

We develop a new, group-theoretic approach to bounding the exponent of matrix multiplication. There are two components to this approach: (1) identifying groups G that admit a certain type of embedding of matrix multiplication into the group…

Group Theory · Mathematics 2012-03-15 Henry Cohn , Christopher Umans

Modular exponentiation is crucial to number theory and cryptography, yet remains largely unexplored from a mechanistic interpretability standpoint. We train a 4-layer encoder-decoder Transformer model to perform this operation and…

Machine Learning · Computer Science 2025-10-24 David Demitri Africa , Sara M. Kapoor , Theo Simon Sorg , Challenger Mishra

One of the major promises of quantum computing is the realization of SIMD (single instruction - multiple data) operations using the phenomenon of superposition. Since the dimension of the state space grows exponentially with the number of…

Multi-term floating-point addition appears in vector dot-product computations, matrix multiplications, and other forms of floating-point data aggregation. A critical step in multi-term floating point addition is the alignment of fractions…

Hardware Architecture · Computer Science 2024-10-30 Kosmas Alexandridis , Giorgos Dimitrakopoulos

Mixed-precision quantization offers superior performance to fixed-precision quantization. It has been widely used in signal processing, communication systems, and machine learning. In mixed-precision quantization, bit allocation is…

Signal Processing · Electrical Eng. & Systems 2025-06-17 Yiming Fang , Li Chen , Yunfei Chen , Weidong Wang , Changsheng You

During the last decades, many studies have been dedicated to improving the performance of neural networks, for example, the network architectures, initialization, and activation. However, investigating the importance and effects of…

Computer Vision and Pattern Recognition · Computer Science 2023-01-12 Fahad Alrasheedi , Xin Zhong , Pei-Chi Huang

We propose networked exponential families to jointly leverage the information in the topology as well as the attributes (features) of networked data points. Networked exponential families are a flexible probabilistic model for heterogeneous…

Machine Learning · Computer Science 2019-09-26 Alexander Jung
‹ Prev 1 4 5 6 7 8 10 Next ›