Search Results for author: Krishna Pillutla

Found 16 papers, 12 papers with code

Distributionally Robust Optimization with Bias and Variance Reduction

no code implementations21 Oct 2023 Ronak Mehta, Vincent Roulet, Krishna Pillutla, Zaid Harchaoui

We consider the distributionally robust optimization (DRO) problem with spectral risk-based uncertainty set and $f$-divergence penalty.

Fairness

User Inference Attacks on Large Language Models

no code implementations13 Oct 2023 Nikhil Kandpal, Krishna Pillutla, Alina Oprea, Peter Kairouz, Christopher A. Choquette-Choo, Zheng Xu

Fine-tuning is a common and effective method for tailoring large language models (LLMs) to specialized tasks and applications.

Correlated Noise Provably Beats Independent Noise for Differentially Private Learning

no code implementations10 Oct 2023 Christopher A. Choquette-Choo, Krishnamurthy Dvijotham, Krishna Pillutla, Arun Ganesh, Thomas Steinke, Abhradeep Thakurta

We characterize the asymptotic learning utility for any choice of the correlation function, giving precise analytical bounds for linear regression and as the solution to a convex program for general convex functions.

Modified Gauss-Newton Algorithms under Noise

no code implementations18 May 2023 Krishna Pillutla, Vincent Roulet, Sham Kakade, Zaid Harchaoui

Gauss-Newton methods and their stochastic version have been widely used in machine learning and signal processing.

Structured Prediction

MAUVE Scores for Generative Models: Theory and Practice

1 code implementation30 Dec 2022 Krishna Pillutla, Lang Liu, John Thickstun, Sean Welleck, Swabha Swayamdipta, Rowan Zellers, Sewoong Oh, Yejin Choi, Zaid Harchaoui

We present MAUVE, a family of comparison measures between pairs of distributions such as those encountered in the generative modeling of text or images.

Quantization

Stochastic Optimization for Spectral Risk Measures

1 code implementation10 Dec 2022 Ronak Mehta, Vincent Roulet, Krishna Pillutla, Lang Liu, Zaid Harchaoui

Spectral risk objectives - also called $L$-risks - allow for learning systems to interpolate between optimizing average-case performance (as in empirical risk minimization) and worst-case performance on a task.

Stochastic Optimization

Statistical and Computational Guarantees for Influence Diagnostics

1 code implementation8 Dec 2022 Jillian Fisher, Lang Liu, Krishna Pillutla, Yejin Choi, Zaid Harchaoui

Influence diagnostics such as influence functions and approximate maximum influence perturbations are popular in machine learning and in AI domain applications.

Federated Learning with Partial Model Personalization

2 code implementations8 Apr 2022 Krishna Pillutla, Kshitiz Malik, Abdelrahman Mohamed, Michael Rabbat, Maziar Sanjabi, Lin Xiao

We consider two federated learning algorithms for training partially personalized models, where the shared and personal parameters are updated either simultaneously or alternately on the devices.

Federated Learning

Federated Learning with Superquantile Aggregation for Heterogeneous Data

1 code implementation17 Dec 2021 Krishna Pillutla, Yassine Laguel, Jérôme Malick, Zaid Harchaoui

We present a federated learning framework that is designed to robustly deliver good predictive performance across individual clients with heterogeneous data.

Federated Learning

MAUVE: Measuring the Gap Between Neural Text and Human Text using Divergence Frontiers

3 code implementations NeurIPS 2021 Krishna Pillutla, Swabha Swayamdipta, Rowan Zellers, John Thickstun, Sean Welleck, Yejin Choi, Zaid Harchaoui

As major progress is made in open-ended text generation, measuring how close machine-generated text is to human language remains a critical open problem.

Text Generation

Device Heterogeneity in Federated Learning: A Superquantile Approach

1 code implementation arXiv preprint 2020 Yassine Laguel, Krishna Pillutla, Jérôme Malick, Zaid Harchaoui

We propose a federated learning framework to handle heterogeneous client devices which do not conform to the population data distribution.

Federated Learning

Robust Aggregation for Federated Learning

2 code implementations arXiv preprint 2019 Krishna Pillutla, Sham M. Kakade, Zaid Harchaoui

We present a robust aggregation approach to make federated learning robust to settings when a fraction of the devices may be sending corrupted updates to the server.

Additive models Federated Learning +1

Cannot find the paper you are looking for? You can Submit a new open access paper.