Skip to main content

Utility navigation

  • Calendar
  • Contact
  • Login
  • MAKE A GIFT
Berkeley University of California
Home Home

Main navigation

  • Programs & Events
    • Research Programs
    • Workshops & Symposia
    • Public Lectures
    • Research Pods
    • Internal Program Activities
    • Algorithms, Society, and the Law
  • Participate
    • Apply to Participate
    • Propose a Program
    • Postdoctoral Research Fellowships
    • Law and Society Fellowships
    • Science Communicator in Residence Program
    • Circles
    • Breakthroughs Workshops and Goldwasser Exploratory Workshops
  • People
    • Scientific Leadership
    • Staff
    • Current Long-Term Visitors
    • Research Fellows
    • Postdoctoral Researchers
    • Scientific Advisory Board
    • Governance Board
    • Affiliated Faculty
    • Science Communicators in Residence
    • Law and Society Fellows
    • Chancellor's Professors
  • News & Videos
    • News
    • Videos
  • Support for the Institute
    • Annual Fund
    • All Funders
    • Institutional Partnerships
  • For Visitors
    • Visitor Guide
    • Plan Your Visit
    • Location & Directions
    • Accessibility
    • Building Access
    • IT Guide
  • About

Results 2111 - 2120 of 23898

Learn more
People

Eddy Yicong

Eddy is a first year PhD student in the School of computational science and engineering at Georgia Institute of Technology advised by Helen Xu. He completed his undergraduate degree in the Computer Science Specialist program at the University of Toronto in...

People

Fulvio Gesmundo

Fulvio Gesmundo is a Junior Professor at the Institut de Mathématiques de Toulouse. His research interest is in Algebraic Geometry Algebraic Geometry and Representation Theory, with a focus toward problems originating in Theoretical Computer Science and...

People

Seyed Khashaiar Gatmiry

Khashayar is a final-year PhD student in the EECS department at MIT, co-advised by Stefanie Jegelka and Jonathan A. Kelner. His research spans machine learning and optimization, with a focus on improving the efficiency and reliability of our training...

People

Jordan Docter

Jordan Docter is currently at Stanford University and their research interests are quantum algorithms and quantum cryptography.

People

Yuki Shirakawa

Yuki Shirakawa is a graduate student at Kyoto University. His research interests are quantum cryptography and quantum advantage.

Image

Welcome, Summer 2025 Visitors!

Check out our Visitor Guide for information to help you make the most of your stay.

Visitor Guide
Visitor Guide
Workshop Talk
|
May 2, 2025

Robust Algorithmic Recourse with Predictions

Algorithmic recourse provides individuals who received an undesirable outcome by machine learning models with suggestions of minimum-cost improvements they can make to achieve a desirable outcome in the future. However, machine learning models often get updated over time and this can cause a recourse to become invalid (i.e., not lead to the desirable outcome). The robust recourse literature aims to choose recourses that are less sensitive, even against adversarial model changes, but this comes at a higher cost. To overcome this obstacle, we initiate the study of algorithmic recourse through the learning-augmented framework and evaluate the extent to which a designer equipped with a prediction regarding future model changes can reduce the cost of recourse when the prediction is accurate (consistency) while also limiting the cost even when the prediction is inaccurate (robustness). We propose a novel algorithm for this problem, study the robustness-consistency trade-off, and analyze how prediction accuracy affects performance.

Workshop Talk
|
May 2, 2025

Synthesizing Pareto-optimal Interpretations of Black Box ML Models

Synthesizing "explainable" interpretations of black-box ML models is often crucial for reasoning about their behaviour. Decision trees and decision diagrams have typically been considered good for explanations, and parameters like depth, count of decision nodes, preference of decision predicates etc. have been used to quantify their "explainability" in different contexts. Almost inevitably, there is a tension between such explainability metrics and the accuracy of the interpretation. Simpler models score high on explainability, but may not faithfully mimic the behaviour of the model; similarly, more complex (and less explainable) models typically do a better job of mimicing the behaviour of a black box model. In this talk, we will discuss how Pareto-optimal interpretations of such black-box models can be systematically synthesized for a large class of explainability metrics using an optimized search based on MaxSAT solving. We provide PAC-style guarantees on the synthesized interpretations, and apply this technique to synthesize Pareto-optimal interpretations of some benchmarks. Our results show that there are often several Pareto-optimal interpretations that are easy to miss if one optimizes a single scalar objective function that combines accuracy and explainability metrics. 

This is joint work with Hazem Torfah, Shetal Shah, Sanjit Seshia and S. Akshay

Pagination

  • Previous page Previous
  • Page 210
  • Page 211
  • Current page 212
  • Page 213
  • Page 214
  • Next page Next
Home
The Simons Institute for the Theory of Computing is the world's leading venue for collaborative research in theoretical computer science.

Footer

  • Programs & Events
  • Participate
  • Workshops & Symposia
  • Contact Us
  • Calendar
  • Accessibility

Footer social media

  • Twitter
  • Facebook
  • Youtube
© 2013–2026 Simons Institute for the Theory of Computing. All Rights Reserved.
link to homepage

Main navigation

  • Programs & Events
    • Research Programs
    • Workshops & Symposia
    • Public Lectures
    • Research Pods
    • Internal Program Activities
    • Algorithms, Society, and the Law
  • Participate
    • Apply to Participate
    • Propose a Program
    • Postdoctoral Research Fellowships
    • Law and Society Fellowships
    • Science Communicator in Residence Program
    • Circles
    • Breakthroughs Workshops and Goldwasser Exploratory Workshops
  • People
    • Scientific Leadership
    • Staff
    • Current Long-Term Visitors
    • Research Fellows
    • Postdoctoral Researchers
    • Scientific Advisory Board
    • Governance Board
    • Affiliated Faculty
    • Science Communicators in Residence
    • Law and Society Fellows
    • Chancellor's Professors
  • News & Videos
    • News
    • Videos
  • Support for the Institute
    • Annual Fund
    • All Funders
    • Institutional Partnerships
  • For Visitors
    • Visitor Guide
    • Plan Your Visit
    • Location & Directions
    • Accessibility
    • Building Access
    • IT Guide
  • About

Utility navigation

  • Calendar
  • Contact
  • Login
  • MAKE A GIFT
link to homepage