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.

168,786 papers · 148 categories

Trend · papers per month

count % of corpus

5 results for “k-optimal”

LoRMIkA: Local rule-based model interpretability with k-optimal associationscs.LG

LoRMIkA finds k-optimal association rules for local model interpretability.

problem Ensuring trust in machine learning predictions.

method Model-agnostic approach using k-optimal association rules from a neighbourhood.

result Achieves competitive results in local accuracy and interpretability.

machine learning interpretability association rules local model k-optimal

2019-08-11abs ↗pdf ↗

Solutions to the

σ_k

-Loewner-Nirenberg problem on annuli are locally Lipschitz and not differentiablemath.AP

Solutions to a specific problem are shown to be locally Lipschitz but not differentiable.

problem Locally Lipschitz viscosity solutions to the

σ_k

-Loewner-Nirenberg problem on annuli.

method Analytical proof of regularity and non-differentiability.

result Solutions are $C^{1,rac{1}{k}}_{ m loc}$ in each of the annulus regions and have a jump in radial derivative.

viscosity solutions Loewner-Nirenberg problem annuli locally Lipschitz non-differentiable

2020-01-13abs ↗pdf ↗

Differentiable Top-k Operator with Optimal Transportcs.LG

Smoothed top-k operator improves model training efficiency.

problem Discontinuous top-k operation makes models untrainable end-to-end.

method SOFT top-k operator approximates top-k as EOT solution.

result Improved performance in k-nearest neighbors and beam search.

top-k optimal transport gradient descent information retrieval machine learning

2020-02-16abs ↗pdf ↗

Generalizing Bayesian Optimization with Decision-theoretic Entropiesstat.ML

This paper generalizes BO uncertainty measures using decision-theoretic entropies.

problem Efficiently inferring optima of expensive black-box functions.

method Introduces a generalized entropy measure from statistical decision theory to optimize Bayesian optimization.

result Demonstrates strong empirical performance across various sequential decision-making tasks.

Bayesian optimization decision-theoretic entropy information theory downstream task loss function

2022-10-04abs ↗pdf ↗

Strategic Decision-Making in the Presence of Information Asymmetry: Provably Efficient RL with Algorithmic Instrumentsstat.ML

New algorithm learns optimal policies in strategic MDPs with private types.

problem Optimal policy learning in strategic MDPs with private types and information asymmetry.

method PLAN algorithm using instrumental variable regression and pessimism principle.

result PLAN achieves near-optimal policy with

1 / \sqrt{K}

optimality.

reinforcement learning strategic decision-making information asymmetry instrumental variables myopic agents

2022-08-23abs ↗pdf ↗