Balle, Borja

40 publications

ICLR 2025 DiSK: Differentially Private Optimizer with Simplified Kalman Filter for Noise Reduction Xinwei Zhang, Zhiqi Bu, Borja Balle, Mingyi Hong, Meisam Razaviyayn, Vahab Mirrokni

TMLR 2025 Preserving Expert-Level Privacy in Offline Reinforcement Learning Navodita Sharma, Vishnu Vinod, Abhradeep Guha Thakurta, Alekh Agarwal, Borja Balle, Christoph Dann, Aravindan Raghuveer

TMLR 2025 Privacy Awareness for Information-Sharing Assistants: A Case-Study on Form-Filling with Contextual Integrity Sahra Ghalebikesabi, Eugene Bagdasarian, Ren Yi, Itay Yona, Ilia Shumailov, Aneesh Pappu, Chongyang Shi, Laura Weidinger, Robert Stanforth, Leonard Berrada, Pushmeet Kohli, Po-Sen Huang, Borja Balle

ICML 2025 Scaling Laws for Differentially Private Language Models Ryan Mckenna, Yangsibo Huang, Amer Sinha, Borja Balle, Zachary Charles, Christopher A. Choquette-Choo, Badih Ghazi, Georgios Kaissis, Ravi Kumar, Ruibo Liu, Da Yu, Chiyuan Zhang

ICLR 2025 The Last Iterate Advantage: Empirical Auditing and Principled Heuristic Analysis of Differentially Private SGD Milad Nasr, Thomas Steinke, Borja Balle, Christopher A. Choquette-Choo, Arun Ganesh, Matthew Jagielski, Jamie Hayes, Abhradeep Guha Thakurta, Adam Smith, Andreas Terzis

NeurIPS 2025 Unifying Re-Identification, Attribute Inference, and Data Reconstruction Risks in Differential Privacy Bogdan Kulynych, Juan Felipe Gomez, Georgios Kaissis, Jamie Hayes, Borja Balle, Flavio Calmon, Jean Louis Raisaro

ICML 2024 Beyond the Calibration Point: Mechanism Comparison in Differential Privacy Georgios Kaissis, Stefan Kolek, Borja Balle, Jamie Hayes, Daniel Rueckert

NeurIPSW 2024 DiSK: Differentially Private Optimizer with Simplified Kalman Filter for Noise Reduction Xinwei Zhang, Zhiqi Bu, Borja Balle, Mingyi Hong, Meisam Razaviyayn, Vahab Mirrokni

AISTATS 2024 On the Privacy of Selection Mechanisms with Gaussian Noise Jonathan Lebensold, Doina Precup, Borja Balle

NeurIPS 2023 Bounding Training Data Reconstruction in DP-SGD Jamie Hayes, Borja Balle, Saeed Mahloujifar

UAI 2023 Mnemonist: Locating Model Parameters That Memorize Training Examples Ali Shahin Shamsabadi, Jamie Hayes, Borja Balle, Adrian Weller

NeurIPSW 2021 Reconstructing Training Data with Informed Adversaries Borja Balle, Giovanni Cherubin, Jamie Hayes

ICLR 2020 A Framework for Robustness Certification of Smoothed Classifiers Using F-Divergences Krishnamurthy Dvijotham, Jamie Hayes, Borja Balle, Zico Kolter, Chongli Qin, Andras Gyorgy, Kai Xiao, Sven Gowal, Pushmeet Kohli

AISTATS 2020 Hypothesis Testing Interpretations and Renyi Differential Privacy Borja Balle, Gilles Barthe, Marco Gaboardi, Justin Hsu, Tetsuya Sato

AISTATS 2020 Local Differential Privacy for Sampling Hisham Husain, Borja Balle, Zac Cranko, Richard Nock

AISTATS 2020 Model-Agnostic Counterfactual Explanations for Consequential Decisions Amir-Hossein Karimi, Gilles Barthe, Borja Balle, Isabel Valera

NeurIPS 2020 Privacy Amplification via Random Check-Ins Borja Balle, Peter Kairouz, Brendan McMahan, Om Thakkar, Abhradeep Guha Thakurta

ICML 2020 Private Reinforcement Learning with PAC and Regret Guarantees Giuseppe Vietri, Borja Balle, Akshay Krishnamurthy, Steven Wu

NeurIPS 2019 Privacy Amplification by Mixing and Diffusion Mechanisms Borja Balle, Gilles Barthe, Marco Gaboardi, Joseph Geumlek

AISTATS 2019 Subsampled Renyi Differential Privacy and Analytical Moments Accountant Yu-Xiang Wang, Borja Balle, Shiva Prasad Kasiviswanathan

ICML 2018 Improving the Gaussian Mechanism for Differential Privacy: Analytical Calibration and Optimal Denoising Borja Balle, Yu-Xiang Wang

AAAI 2018 Learning Predictive State Representations from Non-Uniform Sampling Yuri Grinberg, Hossein Aboutalebi, Melanie Lyman-Abramovitch, Borja Balle, Doina Precup

NeurIPS 2018 Privacy Amplification by Subsampling: Tight Analyses via Couplings and Divergences Borja Balle, Gilles Barthe, Marco Gaboardi

NeurIPS 2017 Hierarchical Methods of Moments Matteo Ruffini, Guillaume Rabusseau, Borja Balle

NeurIPS 2017 Multitask Spectral Learning of Weighted Automata Guillaume Rabusseau, Borja Balle, Joelle Pineau

ICML 2017 Spectral Learning from a Single Trajectory Under Finite-State Policies Borja Balle, Odalric-Ambrym Maillard

ICML 2016 Differentially Private Policy Evaluation Borja Balle, Maziar Gomrokchi, Doina Precup

IJCAI 2016 Learning Multi-Step Predictive State Representations Lucas Langer, Borja Balle, Doina Precup

AISTATS 2016 Low-Rank Approximation of Weighted Tree Automata Guillaume Rabusseau, Borja Balle, Shay B. Cohen

AAAI 2016 Multitask Generalized Eigenvalue Program Boyu Wang, Joelle Pineau, Borja Balle

UAI 2015 Learning and Planning with Timing Information in Markov Decision Processes Pierre-Luc Bacon, Borja Balle, Doina Precup

ALT 2015 On the Rademacher Complexity of Weighted Automata Borja Balle, Mehryar Mohri

MLJ 2014 Adaptively Learning Probabilistic Deterministic Automata from Data Streams Borja Balle, Jorge Castro, Ricard Gavaldà

ICML 2014 Methods of Moments for Learning Stochastic Languages: Unified Presentation and Empirical Comparison Borja Balle, William Hamilton, Joelle Pineau

MLJ 2014 Spectral Learning of Weighted Automata - A Forward-Backward Perspective Borja Balle, Xavier Carreras, Franco M. Luque, Ariadna Quattoni

ICML 2014 Spectral Regularization for Max-Margin Sequence Tagging Ariadna Quattoni, Borja Balle, Xavier Carreras, Amir Globerson

ICML 2012 Local Loss Optimization in Operator Models: A New Insight into Spectral Learning Borja Balle, Ariadna Quattoni, Xavier Carreras

NeurIPS 2012 Spectral Learning of General Weighted Automata via Constrained Matrix Completion Borja Balle, Mehryar Mohri

ECML-PKDD 2011 A Spectral Learning Algorithm for Finite State Transducers Borja Balle, Ariadna Quattoni, Xavier Carreras

ALT 2010 A Lower Bound for Learning Distributions Generated by Probabilistic Automata Borja Balle, Jorge Castro, Ricard Gavaldà