65 citations · 255 across the 23 of their papers we have counts for
23 papers
Gemma 4 Technical Report
Gemma Team, Sherif El Abd, Vaibhav Aggarwal +320
We introduce Gemma 4, a new generation of open-weight, natively multimodal language models in the Gemma model family. Designed to advance compute efficiency and reasoning, the Gemm…
FoodSense: A Multisensory Food Dataset and Benchmark for Predicting Taste, Smell, Texture, and Sound from Images
Sabab Ishraq, Aarushi Aarushi, Juncai Jiang +1
Humans routinely infer taste, smell, texture, and even sound from food images a phenomenon well studied in cognitive science. However, prior vision language research on food has fo…
Statistical Learning from Attribution Sets
Lorne Applebaum, Robert Busa-Fekete, August Y. Chen +3
We address the problem of training conversion prediction models in advertising domains under privacy constraints, where direct links between ad clicks and conversions are unavailab…
TBDFiltering: Sample-Efficient Tree-Based Data Filtering
Robert Istvan Busa-Fekete, Julian Zimmert, Anne Xiangyi Zheng +2
The quality of machine learning models depends heavily on their training data. Selecting high-quality, diverse training sets for large language models (LLMs) is a difficult task, d…
Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
Gheorghe Comanici, Eric Bieber, Mike Schaekermann +3431
In this report, we introduce the Gemini 2.X model family: Gemini 2.5 Pro and Gemini 2.5 Flash, as well as our earlier Gemini 2.0 Flash and Flash-Lite models. Gemini 2.5 Pro is our…
Nearly Optimal Sample Complexity for Learning with Label Proportions
Robert Busa-Fekete, Travis Dick, Claudio Gentile +3
We investigate Learning from Label Proportions (LLP), a partial information setting where examples in a training set are grouped into bags, and only aggregate label values in each…
Near-optimal algorithms for private estimation and sequential testing of collision probability
Robert Busa-Fekete, Umar Syed
We present new algorithms for estimating and testing \emph{collision probability}, a fundamental measure of the spread of a discrete distribution that is widely used in many scient…
Gemma 3 Technical Report
Gemma Team, Aishwarya Kamath, Johan Ferret +209
We introduce Gemma 3, a multimodal addition to the Gemma family of lightweight open models, ranging in scale from 1 to 27 billion parameters. This version introduces vision underst…
A Scalable Crawling Algorithm Utilizing Noisy Change-Indicating Signals
Róbert Busa-Fekete, Julian Zimmert, András György +6
Web refresh crawling is the problem of keeping a cache of web pages fresh, that is, having the most recent copy available when a page is requested, given a limited bandwidth availa…
Auditing Privacy Mechanisms via Label Inference Attacks
Róbert István Busa-Fekete, Travis Dick, Claudio Gentile +3
We propose reconstruction advantage measures to audit label privatization mechanisms. A reconstruction advantage measure quantifies the increase in an attacker's ability to infer t…
Assessing Web Fingerprinting Risk
Enrico Bacis, Igor Bilogrevic, Robert Busa-Fekete +3
Modern Web APIs allow developers to provide extensively customized experiences for website visitors, but the richness of the device information they provide also make them vulnerab…
Private and Communication-Efficient Algorithms for Entropy Estimation
Gecia Bravo-Hermsdorff, Róbert Busa-Fekete, Mohammad Ghavamzadeh +2
Modern statistical estimation is often performed in a distributed setting where each sample belongs to a single user who shares their data with a central server. Users are typicall…
Easy Learning from Label Proportions
Robert Istvan Busa-Fekete, Heejin Choi, Travis Dick +2
We consider the problem of Learning from Label Proportions (LLP), a weakly supervised classification setup where instances are grouped into "bags", and only the frequency of class…
Statistical anonymity: Quantifying reidentification risks without reidentifying users
Gecia Bravo-Hermsdorff, Robert Busa-Fekete, Lee M. Gunderson +2
Data anonymization is an approach to privacy-preserving data release aimed at preventing participants reidentification, and it is an important alternative to differential privacy i…
Probabilistic Label Trees for Extreme Multi-label Classification
Kalina Jasinska-Kobus, Marek Wydmuch, Krzysztof Dembczynski +2
Extreme multi-label classification (XMLC) is a learning task of tagging instances with a small subset of relevant labels chosen from an extremely large pool of possible labels. Pro…
Optimal Learning of Mallows Block Model
Róbert Busa-Fekete, Dimitris Fotakis, Balázs Szörényi +1
The Mallows model, introduced in the seminal paper of Mallows 1957, is one of the most fundamental ranking distribution over the symmetric group . To analyze more complex rank…
On the computational complexity of the probabilistic label tree algorithms
Robert Busa-Fekete, Krzysztof Dembczynski, Alexander Golovnev +4
Label tree-based algorithms are widely used to tackle multi-class and multi-label problems with a large number of labels. We focus on a particular subclass of these algorithms that…
Learning to Crawl
Utkarsh Upadhyay, Robert Busa-Fekete, Wojciech Kotlowski +2
Web crawling is the problem of keeping a cache of webpages fresh, i.e., having the most recent copy available when a page is requested. This problem is usually coupled with the nat…
A no-regret generalization of hierarchical softmax to extreme multi-label classification
Marek Wydmuch, Kalina Jasinska, Mikhail Kuznetsov +2
Extreme multi-label classification (XMLC) is a problem of tagging an instance with a small subset of relevant labels chosen from an extremely large pool of possible labels. Large l…
Preference-based Online Learning with Dueling Bandits: A Survey
Viktor Bengs, Robert Busa-Fekete, Adil El Mesaoudi-Paul +1
In machine learning, the notion of multi-armed bandits refers to a class of online learning problems, in which an agent is supposed to simultaneously explore and exploit a given se…
Distributed Stochastic Optimization via Adaptive SGD
Ashok Cutkosky, Robert Busa-Fekete
Stochastic convex optimization algorithms are the most popular way to train machine learning models on large-scale data. Scaling up the training process of these models is crucial,…
Multi-objective Bandits: Optimizing the Generalized Gini Index
Robert Busa-Fekete, Balazs Szorenyi, Paul Weng +1
We study the multi-armed bandit (MAB) problem where the agent receives a vectorial feedback that encodes many possibly competing objectives to be optimized. The goal of the agent i…
Fast classification using sparse decision DAGs
Djalel Benbouzid, Robert Busa-Fekete, Balazs Kegl
In this paper we propose an algorithm that builds sparse decision DAGs (directed acyclic graphs) from a list of base classifiers provided by an external learning method such as Ada…