On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,657 papers · 148 categories

Trend · papers per month

count % of corpus

8 results for “omniprediction”

Simultaneous Blackwell Approachability and Applications to Multiclass Omnipredictioncs.DS

Study extends binary omniprediction to multiclass setting with improved sample complexity.

problem Suboptimality bounds for each loss function against infinite comparator family in multiclass prediction.

method Design of a framework for solving Blackwell approachability problems with coupled actions.

result Sample complexity of

\approx \varepsilon^{-(k+1)}

for

\varepsilon

-omniprediction in a

k

-class problem.

omniprediction multiclass prediction Blackwell approachability sample complexity regret horizon

2026-02-19abs ↗pdf ↗

Oracle Efficient Online Multicalibration and Omnipredictioncs.LG

New algorithm for online omniprediction with strong guarantees for continuous hypothesis classes.

problem Online adversarial learning with continuous hypothesis classes.

method Developed an oracle-efficient online multicalibration algorithm for infinite benchmark classes.

result First efficient online omnipredictor with strong guarantees for Lipschitz convex loss functions.

online learning multicalibration omniprediction oracle efficiency continuous hypothesis classes

2023-07-18abs ↗pdf ↗

Improved Bounds for Swap Multicalibration and Swap Omnipredictioncs.LG

Improved bounds for multicalibration and omniprediction in online and distributional settings.

problem Achieving efficient multicalibration and omniprediction in fairness and loss minimization.

method Proposed an efficient algorithm achieving improved rates for multicalibration and omniprediction.

result Achieved

O(T^{\frac{1}{3}})

\ell_{2}

-swap multicalibration error for convex Lipschitz functions.

fairness multicalibration omniprediction online learning distributional settings

2025-05-27abs ↗pdf ↗

Near-Optimal Algorithms for Omnipredictionstat.ML

Near-optimal algorithms for predicting across multiple loss functions efficiently.

problem Predicting optimally across various loss functions simultaneously.

method Developed near-optimal online and offline learning algorithms for omniprediction.

result Achieved near-optimal complexity for both online and offline settings.

omniprediction online learning offline learning near-optimal algorithms regret minimization

2025-01-28abs ↗pdf ↗

Agnostically Learning Single-Index Models using Omnipredictorscs.LG

New method learns SIMs with arbitrary monotone activations without strong distributional assumptions.

problem Learning Single-Index Models with arbitrary monotone activations.

method Based on omniprediction with calibrated multiaccuracy and Bregman divergences.

result First agnostic learning result for SIMs with arbitrary monotone activations.

Single-Index Models Agnostic Learning Omniprediction Calibrated Multiaccuracy Bregman Divergences

2023-06-18abs ↗pdf ↗

Omnipredicting Single-Index Models with Multi-Index Modelscs.LG

New algorithm reduces sample complexity for omnipredictors of SIMs.

problem Learning optimal predictors for various loss functions.

method Sharp analysis of Isotron algorithm for agnostic learning.

result Improved sample complexity to

\approx \varepsilon^{-2}

for bi-Lipschitz link functions.

Omnipredictors Single-Index Models Multi-Index Models Agnostic Learning Isotron Algorithm

2024-11-20abs ↗pdf ↗

Making Decisions under Outcome Performativitycs.LG

New approach tackles decision-making under predictions that shape outcomes.

problem Challenges in learning optimal decision rules when predictions influence outcomes.

method Introduces performative omniprediction, a predictor that encodes optimal decision rules for multiple objectives.

result Efficient performative omnipredictors exist under a natural restriction of outcome performativity.

outcome performativity decision-making predictions optimal decision rules supervised learning

2022-10-04abs ↗pdf ↗

Optimal Deterministic Multicalibration and Omnipredictioncs.LG

We resolve the open problem of optimal sample complexity for multicalibration and deterministic predictors.

problem Optimal sample complexity for multicalibration and deterministic predictors

method Minimax-optimal multicalibration algorithm and generalization to OI predictors

result Minimax-optimal multicalibration algorithm and deterministic predictors with optimal sample complexity

multicalibration sample complexity deterministic predictors outcome indistinguishability

2026-06-18abs ↗pdf ↗