English
Related papers

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

200 papers

We consider the problem of solving floating-point constraints obtained from software verification. We present UppSAT --- a new implementation of a systematic approximation refinement framework [ZWR17] as an abstract SMT solver. Provided…

Logic in Computer Science · Computer Science 2017-12-12 Aleksandar Zeljic , Peter Backeman , Christoph M. Wintersteiger , Philipp Ruemmer

State-of-the-art generic low-precision training algorithms use a mix of 16-bit and 32-bit precision, creating the folklore that 16-bit hardware compute units alone are not enough to maximize model accuracy. As a result, deep learning…

Machine Learning · Computer Science 2021-03-09 Pedram Zamirai , Jian Zhang , Christopher R. Aberger , Christopher De Sa

Deep sequence models typically degrade in accuracy when test sequences significantly exceed their training lengths, yet many critical tasks--such as algorithmic reasoning, multi-step arithmetic, and compositional generalization--require…

Machine Learning · Computer Science 2025-12-24 Philip Heejun Lee

Pooling-based recurrent neural architectures consistently outperform their counterparts without pooling. However, the reasons for their enhanced performance are largely unexamined. In this work, we examine three commonly used pooling…

Computation and Language · Computer Science 2020-10-29 Pratyush Maini , Keshav Kolluru , Danish Pruthi , Mausam

A well-known generalisation of positional numeration systems is the case where the base is the residue class of $x$ modulo a given polynomial $f(x)$ with coefficients in (for example) the integers, and where we try to construct finite…

Number Theory · Mathematics 2011-06-22 Christiaan E. van de Woestijne

Training Deep Neural Networks (DNNs) can be computationally demanding, particularly when dealing with large models. Recent work has aimed to mitigate this computational challenge by introducing 8-bit floating-point (FP8) formats for…

Hardware Architecture · Computer Science 2024-09-27 Sami Ben Ali , Silviu-Ioan Filip , Olivier Sentieys

In this paper, we investigate optimization problems with nonnegative and orthogonal constraints, where any feasible matrix of size $n \times p$ exhibits a sparsity pattern such that each row accommodates at most one nonzero entry. Our…

Optimization and Control · Mathematics 2025-11-06 Lei Wang , Xin Liu , Xiaojun Chen

Floating-point accumulation networks (FPANs) are key building blocks used in many floating-point algorithms, including compensated summation and double-double arithmetic. FPANs are notoriously difficult to analyze, and algorithms using…

Numerical Analysis · Mathematics 2025-05-27 David K. Zhang , Alex Aiken

Non-trivial analysis problems require posets with infinite ascending and descending chains. In order to compute reasonably precise post-fixpoints of the resulting systems of equations, Cousot and Cousot have suggested accelerated fixpoint…

Programming Languages · Computer Science 2015-03-04 Gianluca Amato , Francesca Scozzari , Helmut Seidl , Kalmer Apinis , Vesal Vojdani

In numeric-intensive computations, it is well known that the execution of floating-point programs is imprecise as floating-point arithmetic incurs round-off errors. Although round-off errors are small for a single floating-point operation,…

Programming Languages · Computer Science 2026-05-05 Xuran Cai , Liqian Chen , Hongfei Fu

The compression of deep neural networks (DNNs) to reduce inference cost becomes increasingly important to meet realistic deployment requirements of various applications. There have been a significant amount of work regarding network…

Machine Learning · Computer Science 2020-11-12 Tianyi Chen , Bo Ji , Yixin Shi , Tianyu Ding , Biyi Fang , Sheng Yi , Xiao Tu

Although the representation of the real numbers in terms of a base and a set of digits has a long history, new questions arise even in simple situations. This paper concerns binary radix systems, i.e., positional number systems with digits…

Combinatorics · Mathematics 2013-05-29 Andrew Vince

Conditional computation and modular networks have been recently proposed for multitask learning and other problems as a way to decompose problem solving into multiple reusable computational blocks. We propose a new approach for learning…

Machine Learning · Computer Science 2021-07-26 Andrey Zhmoginov , Dina Bashkirova , Mark Sandler

A convergent algorithm for nonnegative matrix factorization with orthogonality constraints imposed on both factors is proposed in this paper. This factorization concept was first introduced by Ding et al. with intent to further improve…

Machine Learning · Computer Science 2018-11-16 Andri Mirzal

In recent years fused-multiply-add (FMA) units with lower-precision multiplications and higher-precision accumulation have proven useful in machine learning/artificial intelligence applications, most notably in training deep neural networks…

Mathematical Software · Computer Science 2019-04-16 Greg Henry , Ping Tak Peter Tang , Alexander Heinecke

The multivariate probit is popular for modeling correlated binary data, with an attractive balance of flexibility and simplicity. However, considerable challenges remain in computation and in devising a clear statistical framework. Interest…

Methodology · Statistics 2020-04-22 Bryan W. Ting , Fred A. Wright , Yi-Hui Zhou

We present a simple baseline for directly estimating the relative pose (rotation and translation, including scale) between two images. Deep methods have recently shown strong progress but often require complex or multi-stage architectures.…

Computer Vision and Pattern Recognition · Computer Science 2023-01-25 Chris Rockwell , Justin Johnson , David F. Fouhey

We propose a novel neural preconditioned Newton (NP-Newton) method for solving parametric nonlinear systems of equations. To overcome the stagnation or instability of Newton iterations caused by unbalanced nonlinearities, we introduce a…

Numerical Analysis · Mathematics 2025-11-13 Youngkyu Lee , Shanqing Liu , Jerome Darbon , George Em Karniadakis

Reducing energy consumption has become a pressing need for modern machine learning, which has achieved many of its most impressive results by scaling to larger and more energy-consumptive neural networks. Unfortunately, the main algorithm…

Machine Learning · Computer Science 2025-07-10 Risi Jaiswal , Supriyo Datta , Joseph G. Makin

Large Language Model training with 8-bit floating point (FP8) formats promises significant efficiency improvements, but reduced numerical precision makes training challenging. It is currently possible to train in FP8 only if one is willing…

Machine Learning · Computer Science 2025-06-06 Saaketh Narayan , Abhay Gupta , Mansheej Paul , Davis Blalock
‹ Prev 1 8 9 10 Next ›