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.

168,742 papers · 148 categories

Trend · papers per month

count % of corpus

4 results for “best-of-three-worlds”

Best-of-three-worlds Analysis for Linear Bandits with Follow-the-regularized-leader Algorithmcs.LG

FTRL algorithm with negative entropy regularizer achieves best-of-three-world results for linear bandits.

problem Designing an FTRL algorithm for linear bandits with optimal regret bounds.

method Follow-the-regularized-leader (FTRL) algorithm with negative entropy regularizer.

result Regret bounds achieve the same or nearly the same order as detect-switch type algorithm but with simpler design.

linear bandits FTRL negative entropy regularizer best-of-three-worlds regret bounds

2023-03-13abs ↗pdf ↗

Best-of-Three-Worlds Linear Bandit Algorithm with Variance-Adaptive Regret Boundscs.LG

Adaptive linear bandit algorithm with best-of-three-worlds regret bounds.

problem Adaptive to adversarial and stochastic environments with varying sub-optimality gaps and corruption.

method Combines SCRiBLe algorithm with scaled-up sampling and optimistic online learning.

result Achieves best-of-three-worlds regret bounds of

O(\sqrt{T \log T})

for adversarial and

O(\frac{\log T}{Δ_{\min}} + \sqrt{\frac{C \log T}{Δ_{\min}}})

for stochastic environments.

linear bandit adaptive algorithms regret bounds adversarial environments stochastic environments

2023-02-24abs ↗pdf ↗

Hybrid Neural Models For Sequence Modelling: The Best Of Three Worldscs.LG

Hybrid model combines RNNs, encoders-decoders, and Transformers for sequence tasks.

problem Sequence labelling tasks

method Combination of bidirectional RNNs, encoder-decoder, and Transformer models

result Results are close to state-of-the-art and better for some tasks

sequence modelling neural models bidirectional RNNs encoder-decoder Transformer

2019-09-16abs ↗pdf ↗

Improved Analysis for Dynamic Regret of Strongly Convex and Smooth Functionscs.LG

Improved dynamic regret analysis for strongly convex and smooth functions.

problem Analyzing dynamic regret for online learning algorithms.

method Improved analysis of the Online Multiple Gradient Descent (OMGD) algorithm.

result Achieved a best-of-three-worlds guarantee for dynamic regret.

dynamic regret strongly convex smooth functions OMGD algorithm path-length

2020-06-10abs ↗pdf ↗