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.
New algorithm reduces sample complexity for omnipredictors of SIMs.
New machine learning paradigm ignores loss function until action time.
New approach tackles decision-making under predictions that shape outcomes.
Near-optimal algorithms for predicting across multiple loss functions efficiently.
New method learns SIMs with arbitrary monotone activations without strong distributional assumptions.
We resolve the open problem of optimal sample complexity for multicalibration and deterministic predictors.
Improved bounds for multicalibration and omniprediction in online and distributional settings.
New algorithm for online omniprediction with strong guarantees for continuous hypothesis classes.