activity
20222024
most citedFedL2P: Federated Learning to Personalize

5 citations · 7 across the 3 of their papers we have counts for

collaborators

7 papers

stat.ML20242 cited

Position: Understanding LLMs Requires More Than Statistical Generalization

Patrik Reizinger, Szilvia Ujváry, Anna Mészáros +3

The last decade has seen blossoming research in deep learning theory attempting to answer, "Why does deep learning generalize?" A powerful shift in perspective precipitated this pr…

stat.ML2024

Identifiable Exchangeable Mechanisms for Causal Structure and Representation Learning

Patrik Reizinger, Siyuan Guo, Ferenc Huszár +2

Identifying latent representations or causal structures is important for good generalization and downstream task performance. However, both fields have been developed rather indepe…

stat.ME2024

Do Finetti: On Causal Effects for Exchangeable Data

Siyuan Guo, Chi Zhang, Karthika Mohan +2

We study causal effect estimation in a setting where the data are not i.i.d. (independent and identically distributed). We focus on exchangeable data satisfying an assumption of in…

cs.LG2024

Recurrent Early Exits for Federated Learning with Heterogeneous Clients

Royson Lee, Javier Fernandez-Marques, Shell Xu Hu +6

Federated learning (FL) has enabled distributed learning of a model across multiple clients in a privacy-preserving manner. One of the main challenges of FL is to accommodate clien…

cs.AI2024

Learning Beyond Pattern Matching? Assaying Mathematical Understanding in LLMs

Siyuan Guo, Aniket Didolkar, Nan Rosemary Ke +3

We are beginning to see progress in language model assisted scientific discovery. Motivated by the use of LLMs as a general scientific assistant, this paper assesses the domain kno…

cs.LG20235 cited

FedL2P: Federated Learning to Personalize

Royson Lee, Minyoung Kim, Da Li +4

Federated learning (FL) research has made progress in developing algorithms for distributed learning of global models, as well as algorithms for local personalization of those comm…