paper-with-me

Papers

Emergent properties with repeated examples

2024-10-09 · François Charton, Julia Kempe

We study the performance of transformers as a function of the number of repetitions of training examples with algorithmically generated datasets. On three problems of mathematics: the greatest common divisor, modular multiplication, and matrix eigenvalues, we show that for a fixed number of training steps, models trained on smaller sets of repeated examples outperform models trained on larger sets of single-use examples. We also demonstrate that two-set training - repeated use of a small random subset of examples, along normal sampling on the rest of the training set - provides for faster learning and better performance. This highlights that the benefits of repetition can outweigh those of data diversity. These datasets and problems provide a controlled setting to shed light on the still poorly understood interplay between generalization and memorization in deep learning.

📄 PDF Abstract BibTeX arXiv:2410.07041

Code (0)

등록된 구현이 없습니다.

Tasks

DiversityMemorization

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

Emergence and Synchronization in Chaotic Oscillators and in the Human Cortical Network

2021-05-22 · Nir Lahav

When we look at the world around us, we see complex physical systems and emergent phenomena. Emergence occurs when a system is observed to have properties that its parts do not have on their own. These properties or beha…

Beehive scale-free emergent dynamics

2023-11-28 · Ivan Shpurov, Tom Froese, Dante R. Chialvo

It has been repeatedly reported that the collective dynamics of social insects exhibit universal emergent properties similar to other complex systems. In this note, we study a previously published data set in which the p…

Emergent predictability in microbial ecosystems

2024-03-28 · Jacob Moran, Mikhail Tikhonov

Microbial ecosystems carry out essential functions for global climate, human health, and industry. These complex communities exhibit a surprising amount of functionally relevant diversity at all levels of taxonomic resol…

Compositional properties of emergent languages in deep learning

2020-01-23 · Bence Keresztury, Elia Bruni

Recent findings in multi-agent deep learning systems point towards the emergence of compositional languages. These claims are often made without exact analysis or testing of the language. In this work, we analyze the eme…

Deep Learning

Emergent and Subliminal Misalignment Through the Lens of Data-Mediated Transfer

2026-05-12 · Baris Askin, Muhammed Ustaomeroglu, Anupam Nayak, Gauri Joshi 외 arxiv

Fine-tuning LLMs on narrow harmful datasets can induce Emergent Misalignment (EM), where models exhibit misaligned behavior far beyond the fine-tuning distribution. We argue that emergent misalignment can be better under…