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.

168,695 papers · 148 categories

Trend · papers per month

count % of corpus

15 results for “Decision-Estimation-Coefficient”

Model-Free Reinforcement Learning with the Decision-Estimation Coefficientcs.LG

Improved model-free reinforcement learning with decision-estimation coefficient.

problem Interactive decision making, including structured bandits and reinforcement learning.

method Combining Estimation-to-Decisions with optimistic estimation to achieve better regret bounds.

result Regret bounds for model-free reinforcement learning with value function approximation.

Reinforcement Learning Model-Free Decision-Estimation Coefficient Interactive Decision Making Optimistic Estimation

2022-11-25abs ↗pdf ↗

On the Complexity of Adversarial Decision Makingcs.LG

New bounds show complexity of adversarial decision making.

problem Understanding sample efficiency in adversarial decision making.

method New upper and lower bounds on Decision-Estimation Coefficient.

result Decision-Estimation Coefficient is necessary and sufficient for low regret in adversarial decision making.

Adversarial Decision Making Regret Minimization Complexity Measures Decision-Estimation Coefficient Reinforcement Learning

2022-06-27abs ↗pdf ↗

Tight Bounds for

γ

-Regret via the Decision-Estimation Coefficientcs.LG

New bounds for $γ$ -regret using modified Decision-Estimation Coefficient.

problem Statistical characterization of

γ

-regret for complex bandit problems.

method Statistical characterization via

γ

-DEC, a modified Decision-Estimation Coefficient.

result Upper and lower bounds for

γ

-regret nearly match, showing fundamental limits.

regret bandit problems Decision-Estimation Coefficient statistical complexity algorithm

2023-03-06abs ↗pdf ↗

Tight Guarantees for Interactive Decision Making with the Decision-Estimation Coefficientcs.LG

New DEC variant improves sample complexity bounds in decision making.

problem Understanding sample-efficient learning guarantees in decision making.

method Introducing a new Constrained Decision-Estimation Coefficient (DEC) and using it to derive improved lower bounds.

result New lower bounds improve upon prior work in three aspects: expectation, global applicability, and improper reference models.

Decision-Estimation Coefficient sample complexity reinforcement learning bandits improper reference models

2023-01-19abs ↗pdf ↗

The Statistical Complexity of Interactive Decision Makingcs.LG

New complexity measure for interactive learning reduces regret to near-optimal levels.

problem Challenges in sample-efficient, adaptive learning algorithms for interactive decision making.

method Introduces the Decision-Estimation Coefficient and the Estimation-to-Decisions (E2D) principle.

result Unified algorithm design principle E2D achieves optimal sample-efficient learning.

interactive decision making regret minimization statistical complexity reinforcement learning supervised estimation

2021-12-27abs ↗pdf ↗

Unified Algorithms for RL with Decision-Estimation Coefficients: PAC, Reward-Free, Preference-Based Learning, and Beyondcs.LG

Unified algorithm tackles various RL goals like reward-free and preference-based learning.

problem Unified approach to multiple RL learning goals.

method Decision-Estimation Coefficient (DEC) framework.

result Unified algorithm handles various learning goals with a single framework.

Reinforcement Learning Unified Algorithms Decision-Estimation Coefficient Reward-Free Preference-Based Learning

2022-09-23abs ↗pdf ↗

Taming the Monster Every Context: Complexity Measure and Unified Framework for Offline-Oracle Efficient Contextual Banditscs.LG

OE2D framework reduces contextual bandits to offline regression for near-optimal regret.

problem Efficiently learning contextual bandits with large action spaces and complex reward functions.

method Offline Estimation to Decisions (OE2D) algorithm that reduces contextual bandits to offline regression.

result Near-optimal regret for contextual bandits with large action spaces and

O(\log T)

calls to an offline regression oracle.

Contextual Bandits Offline Regression Regret Minimization Decision Estimation Coefficient Eluder Dimension

2026-02-10abs ↗pdf ↗

Assouad, Fano, and Le Cam with Interaction: A Unifying Lower Bound Framework and Characterization for Bandit Learnabilitycs.LG

Unified framework for lower bounds in interactive decision making.

problem Challenges in interactive decision making, especially bandits and reinforcement learning.

method Interactive Fano method and Fractional Covering Number.

result Unified characterization of learnability for stochastic bandit problems and tight lower bounds for interactive decision making.

lower bounds interactive decision making bandits reinforcement learning Fano method

2024-10-07abs ↗pdf ↗

A Complete Characterization of Learnability for Stochastic Noisy Banditscs.LG

We characterize learnability for stochastic noisy bandits, identifying optimal query complexities.

problem Learnability of stochastic noisy bandit models.

method Complete characterization through model class analysis and proof of optimal query complexities.

result Characterization of learnability for stochastic noisy bandit models.

Stochastic Noisy Bandits Learnability Model Class Optimal Query Complexity Decision-Estimation-Coefficient

2024-10-12abs ↗pdf ↗

The Sample Complexity of Multiclass and Sparse Contextual Banditscs.LG

New algorithms reduce sample complexity for multiclass contextual bandits.

problem Designing efficient algorithms for multiclass contextual bandits with sparse rewards.

method Two complementary approaches: decision-estimation coefficient analysis and low-variance exploration.

result Achieved optimal sample complexity bounds for multiclass contextual bandits.

Contextual Bandits Multiclass Classification Sparse Rewards Sample Complexity Decision-Estimation Coefficient

2026-05-28abs ↗pdf ↗

Decision Making in Changing Environments: Robustness, Query-Based Learning, and Differential Privacycs.LG

Framework for robust decision making in changing environments with privacy constraints.

problem Interactive decision making in changing environments with constraints.

method Hybrid Decision Making with Structured Observations (hybrid DMSO) framework, local differentially private decision making, query-based learning, robust and smooth decision making.

result Strong connections and bounds derived for DEC, SQ dimension, local minimax complexity, learnability, and joint differential privacy.

decision making changing environments privacy constraints hybrid DMSO local differential privacy

2025-01-24abs ↗pdf ↗

Taming the Monster Every Context: Complexity Measure and Unified Framework for Offline-Oracle Efficient Contextual Banditscs.LG

Framework reduces contextual bandit learning to offline regression with near-optimal regret.

problem Efficient learning with large action spaces and complex reward functions.

method Offline Estimation to Decisions (OE2D) algorithm that minimizes regret with near-optimal oracle calls.

result Near-optimal regret for contextual bandits with large action spaces and

O(log(T))

offline oracle calls.

Contextual Bandits Offline Regression Decision-Offline Estimation Coefficient (DOEC)Eluder Dimension Regret Analysis

2026-02-10abs ↗pdf ↗

Decision Making in Hybrid Environments: A Model Aggregation Approachcs.LG

Improves decision complexity in hybrid environments.

problem Complexity in hybrid decision-making problems.

method General extension of DEC framework, model aggregation approach.

result Improved regret bounds for linear Q*/V* MDPs.

Decision Making Hybrid Environments DEC Framework Model Aggregation Regret Bounds

2025-02-09abs ↗pdf ↗

On the Complexity of Multi-Agent Decision Making: From Learning in Games to Partial Monitoringcs.LG

Study on multi-agent decision making complexity, showing sample efficiency gaps.

problem Understanding sample efficiency in multi-agent decision making.

method General framework for interactive decision making, focusing on equilibrium computation.

result No 'reasonable' complexity measure can close gaps between single and multiple agents.

multi-agent decision making sample complexity equilibrium computation partial monitoring Markov games

2023-05-01abs ↗pdf ↗

On the Complexity of Offline Reinforcement Learning with

Q^\star

-Approximation and Partial Coveragecs.LG

Study shows offline RL under $Q^\star$ -approximation and partial coverage is harder than previously thought.

problem Theoretical limits of offline reinforcement learning under

Q^\star

-approximation and partial coverage.

method Introduced a decision-estimation framework to decompose offline RL complexity into decision and value estimation errors.

result Answered the open question by proving sample inefficiency under partial coverage is not guaranteed by

Q^\star

-realizability and Bellman completeness.

offline reinforcement learning partial coverage information theory decision-estimation Bellman completeness

2026-02-12abs ↗pdf ↗