Nika Haghtalab
where else to find them
no profile links on file
what they talk about
where they keep going back
no series more than once — all 5 in the filters
on a stage with
never shared a talk
who talks about the same things
nobody close enough yet
| title | conference | date |
|---|---|---|
| Multi-objective Learning: An Algorithmic Toolbox for Optimal Predictions Anytime Anywhere! | The Role of TCS in Modern Machine Learning | 2026-05-26 |
Presents a concrete algorithmic toolbox that turns K-fold hard multi-distribution learning into an adaptively sampled problem where sample complexity adds… | ||
| The Truth About Your Lying Calibrated Forecaster: How to Design Truthful Calibration Measures | Joint IFML/MPG Symposium 2024 | 2024-11-19 |
Shows that standard calibration measures like ECE are gameable: a manipulative forecaster gets ECE≈0 while a truthful forecaster pays Θ(√T) variance or even… | ||
| A Theory of Multi-objective Machine Learning | Modern Paradigms in Generalization Boot Camp 2024 | 2024-08-27 |
Introduces a concrete formalism: learn one model good for k distributions (per-distribution losses and calibration), cast as a min‑max game solved by no-regret… | ||
| Oracle-Efficient Online Learning or: How to Use Non-Robust Optimization for Robust Learning | Quantifying Uncertainty: Stochastic, Adversarial, and Beyond | 2022-09-12 |
Claim: efficient no-regret online learning is possible by reusing a standard ERM oracle rather than redesigning algorithms from scratch, provided the adversary… | ||
| Multi-Distribution Learning, for Robustness, Fairness, and Collaboration | Data-Driven Decision Processes Boot Camp 2022 | 2022-08-22 |
Argues that worst-case multi-distribution learning can avoid an O(K) blowup and often needs only log K dependence by recasting the problem as a min‑max game… | ||
| nothing matches | ||