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

3 results for “EFCE”

Sample-Efficient Learning of Correlated Equilibria in Extensive-Form Gamescs.LG

First sample-efficient algorithm for learning EFCE in bandit feedback settings.

problem Learning EFCE in bandit feedback settings for IIEFGs.

method Proposed

K

-EFCE and uncoupled no-regret algorithm with wide-range regret minimization.

result First sample-efficient algorithm for learning EFCE from bandit feedback.

EFCE bandit feedback uncoupled no-regret wide-range regret IIEFGs

2022-05-15abs ↗pdf ↗

Efficient Phi-Regret Minimization in Extensive-Form Games via Online Mirror Descentcs.LG

Paper addresses inefficiency in converting EFGs to NFGs for learning.

problem Inefficiency in converting Extensive-Form Games to Normal-Form Games.

method Uses

Φ

-Hedge algorithm and Online Mirror Descent (OMD) for polynomial-time learning of EFGs.

result Achieves

\widetilde{\mathcal{O}}(\sqrt{XAT})

EFCE-regret, matching information-theoretic lower bound.

Extensive-Form Games Online Mirror Descent EFCE NFCCE Φ-Hedge

2022-05-30abs ↗pdf ↗

Causal Estimation with Functional Confoundersstat.ME

Study functional confounders in causal inference, enabling estimable effects.

problem Causal inference challenges with functional confounders violating positivity.

method Functional interventions, functional positivity, gradient fields, Level-set Orthogonal Descent Estimation (LODE).

result Valid causal effect estimation under certain conditions.

causal inference functional confounders positivity violation functional interventions gradient fields

2021-02-17abs ↗pdf ↗