Junk DNA Hypothesis: Pruning Small Pre-Trained Weights Irreversibly and Monotonically Impairs “Difficult" Downstream Tasks in LLMs
Yin, L Jaiswal, A Liu, S Kundu, S Wang, Z Proceedings of Machine Learning Research volume 235 57053-57068 (01 Jan 2024)
Outlier Weighed Layerwise Sparsity (OWL): A Missing Secret Sauce for Pruning LLMs to High Sparsity
Yin, L Wu, Y Zhang, Z Hsieh, C Wang, Y Jia, Y Li, G Jaiswal, A Pechenizkiy, M Liang, Y Bendersky, M Wang, Z Liu, S Proceedings of Machine Learning Research volume 235 57101-57115 (01 Jan 2024)
Advancing Dynamic Sparse Training by Exploring Optimization Opportunities
Ji, J Li, G Yin, L Qin, M Yuan, G Guo, L Liu, S Ma, X Proceedings of Machine Learning Research volume 235 21606-21619 (01 Jan 2024)
Wed, 27 Nov 2024

17:00 - 18:30
L5

Truth Be Told: How To Interpret Past Mathematicians

A.C. Paseau and Fabian Pregel
(Department of Philosophy, University of Oxford)
Abstract

How should we interpret past mathematicians who may use the same vocabulary as us but with different meanings, or whose philosophical outlooks differ from ours? Errors aside, it is often assumed that past mathematicians largely made true claims—but what exactly justifies that assumption?


In this talk, we will explore these questions through general philosophical considerations and three case studies: 19th-century analysis, 18th-century geometry, and 19th-century matricial algebra.  In each case, we encounter a significant challenge to supposing that the mathematicians in question made true claims. We will show how these challenges can be addressed and overcome.

Isogenies on Kummer surfaces
Corte-Real Santos, M Flynn, E Mathematics of Computation (07 Nov 2024)
Statistical predictions of trading strategies in electronic markets
Cartea, A Cohen, S Graumans, R Labyad, S Sanchez Betancourt, L van Veldhuijzen, L Journal of Financial Econometrics (18 Oct 2024)
On market clearing of day ahead auctions for European power markets: consumer payment minimisation versus social welfare maximisation
Puiu, I Hauser, R Energy Economics volume 139 (12 Sep 2024)
New results on 3d 𝒩=2 SQCD and its 3d GLSM interpretation
Closset, C Khlaif, O International Journal of Modern Physics A volume 39 issue 33 2446011 (30 Nov 2024)
Sparse Cocktail: Every Sparse Pattern Every Sparse Ratio All At Once
Li, Z Liu, S Chen, T Jaiswal, A Zhang, Z Wang, D Krishnamoorthi, R Chang, S Wang, Z Proceedings of Machine Learning Research volume 235 28368-28386 (01 Jan 2024)
Subscribe to