activity
20242026
collaborators
Showing cs.LGShow all

6 papers · 1 filter

cs.LG2026

On the Convergence of Multicalibration Gradient Boosting

Daniel Haimovich, Fridolin Linder, Lorenzo Perini +2

Multicalibration gradient boosting has recently emerged as a scalable method that empirically produces approximately multicalibrated predictors and has been deployed at web scale.…

cs.LG2026

Billion-Scale Graph Foundation Models

Maya Bechler-Speicher, Yoel Gottlieb, Andrey Isakov +5

Graph-structured data underpins many critical applications. While foundation models have transformed language and vision via large-scale pretraining and lightweight adaptation, ext…

cs.LG2026

MCGrad: Multicalibration at Web Scale

Niek Tax, Lorenzo Perini, Fridolin Linder +5

We propose MCGrad, a novel and scalable multicalibration algorithm. Multicalibration - calibration in subgroups of the data - is an important property for the performance of machin…

cs.LG2025

Multicalibration Yields Better Matchings

Riccardo Colini Baldeschi, Simone Di Gregorio, Simone Fioravanti +9

Consider the problem of finding the best matching in a weighted graph where we only have access to predictions of the actual stochastic weights, based on an underlying context. If…

cs.LG2024

On the Convergence of Loss and Uncertainty-based Active Learning Algorithms

Daniel Haimovich, Dima Karamshuk, Fridolin Linder +2

We investigate the convergence rates and data sample sizes required for training a machine learning model using a stochastic gradient descent (SGD) algorithm, where data points are…

cs.LG2024

Online Learning with Sublinear Best-Action Queries

Matteo Russo, Andrea Celli, Riccardo Colini Baldeschi +5

In online learning, a decision maker repeatedly selects one of a set of actions, with the goal of minimizing the overall loss incurred. Following the recent line of research on alg…