Research
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
1223 · Mar 202619922001200920172026
8 results for “delight”
Does This Gradient Spark Joy?cs.LG

DG improves policy gradient efficiency by selectively backpropagating only valuable samples.

problem Expensive backward passes in policy gradient methods reduce efficiency.
method Introduces 'delight' as a forward-pass signal of learning value and a Kondo gate to selectively backpropagate.
result Selective backpropagation reduces backward pass costs without sacrificing learning quality.
policy gradientbackpropagationdelightKondo gatebandits
2026-03-20abs ↗pdf ↗
Delightful Explorationcs.LG

DE is a new exploration method that limits resource usage based on expected improvement and surprise.

problem Limited exploration in large action spaces when resources are scarce.
method Delight-gated exploration (DE) that limits exploration actions based on a gate price set by the product of expected improvement and surprise.
result DE outperforms ε\varepsilon-greedy and Thompson Sampling in terms of regret across various bandit and MDP settings.
explorationresource allocationbanditssurpriseregret
2026-05-13abs ↗pdf ↗
Delightful Policy Gradientcs.LG

DG improves policy gradients by weighting actions with a sigmoid of advantage and surprisal.

problem Pathologies in standard policy gradients, leading to poor updates and over-allocation of gradient budget.
method Introduces Delightful Policy Gradient (DG) that gates each term with a sigmoid of advantage and surprisal.
result DG provably improves directional accuracy in a single context and shifts the expected gradient closer to the oracle across multiple contexts.
policy gradientsadvantagesurprisalbanditssupervised cross-entropy
2026-03-15abs ↗pdf ↗
Delightful Distributed Policy Gradientcs.LG

DG separates successes and failures by gating updates with advantage and surprisal.

problem Negative learning from surprising data in distributed reinforcement learning.
method DG gates each update with the product of advantage and surprisal, suppressing failures and preserving successes.
result DG outperforms other methods in various challenging reinforcement learning tasks.
reinforcement learningdistributed learningpolicy gradientsurprisaladvantage
2026-03-20abs ↗pdf ↗