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.

169,051 papers · 148 categories

Trend · papers per month

count % of corpus

3 results for “hypentropy”

Exponentiated Gradient Meets Gradient Descentcs.LG

Unified approach combining gradient descent and multiplicative updates.

problem Combining gradient descent and multiplicative updates for machine learning.

method Introduces hypentropy and a family of matrix-based updates.

result Derives tight regret bounds for the new family of updates.

gradient descent multiplicative updates matrix updates regret bounds hypentropy

2019-02-05abs ↗pdf ↗

A Continuous-Time Mirror Descent Approach to Sparse Phase Retrievalstat.ML

Continuous-time mirror descent solves sparse phase retrieval efficiently.

problem Recovering sparse signals from magnitude-only measurements.

method Continuous-time mirror descent applied to unconstrained empirical risk minimization problem.

result Mirror descent recovers

k

-sparse vectors with minimum non-zero entry order of

\| \mathbf{x}^\star \|_2/\sqrt{k}

from

k^2

Gaussian measurements.

sparse phase retrieval mirror descent non-convex optimization sparse signal recovery phaseless sampling

2020-10-20abs ↗pdf ↗

Policy Regret for Embedding Model Routing: Contextual Bandits with Low-Rank Expertscs.LG

New algorithm tackles dynamic query routing to multiple embedding models.

problem Dynamic query routing to multiple embedding models under adversarial conditions.

method Formalized as adversarial contextual linear bandit with low-rank experts, proposed HPG algorithm.

result HPG algorithm achieves linearized policy regret of

ilde{\mathcal O}(s\sqrt{M T})

embedding models contextual bandits policy regret adversarial feedback low-rank structure

2026-06-12abs ↗pdf ↗