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.

168,695 papers · 148 categories

Trend · papers per month

326495127 · Jun 202019922001200920172026
48 results for private RL

Study differential privacy in multi-agent RL, achieving efficient and private learning.

problem Protecting sensitive data in multi-agent reinforcement learning.
method Extending DP definitions to two-player games, designing an efficient algorithm with privatized bonuses.
result Achieved trajectory-wise differential privacy in multi-agent RL, improving regret bounds.

Improved privacy in RL with near-optimal regret bounds.

problem Privacy-preserving reinforcement learning in personalized decision-making systems.
method Differentially private algorithm based on LSVI-UCB++ with privacy-preserving techniques.
result Achieved a near-optimal regret bound of O(d * sqrt(H^3 * K) + H^(15/4) * d^(7/6) * K^(1/2) / ε).

Private RL algorithm with privacy guarantees for personalized medicine decisions.

problem Privacy-preserving reinforcement learning for personalized medicine decisions.
method Developed a private optimism-based RL algorithm using joint differential privacy (JDP).
result Achieved strong PAC and regret bounds with a privacy guarantee.

Paper proposes a privacy-preserving RL algorithm for linear MDPs with theoretical guarantees.

problem Protecting users' private data in personalized services using RL.
method Local differential privacy (LDP) for RL with linear function approximation.
result Achieves a regret bound of $O(d^{5/4}H^{7/4}T^{3/4}\left(\log(1/δ) ight)^{1/4}\sqrt{1/\varepsilon})$ for linear mixture MDPs.

Study human-machine interaction with private info using offline RL.

problem Confounding bias and distributional mismatch in offline RL for human-guided interaction.
method Developed a novel identification result and OPE method to address confounding bias, and used pessimism to tackle distributional mismatch.
result Policy pair converges to optimal one at satisfactory rate under mild assumptions.

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/K1 / \sqrt{K} optimality.

New algorithm for personalized healthcare with privacy guarantees.

problem Online exploration in reinforcement learning with differential privacy constraints.
method ε-JDP algorithm with privately released exploration bonuses and visitation statistics.
result Regret bound of O(SAH2T+S2AH3/ε)O(\sqrt{SAH^2T}+S^2AH^3/ε) matching information-theoretic lower bound.

In the last few years, deep multi-agent reinforcement learning (RL) has become a highly active area of research. A particularly challenging class of problems in this area is partially observable, cooperative, multi-agent learning, in which teams of agents must learn to coordinate their behaviour while conditioning only…

2019-02-11abs ↗pdf ↗

Abstract MDPs enable strategic exploration and fast reward transfer in complex environments.

problem Challenging to learn accurate MDPs for high-dimensional states.
method Learn an abstract MDP over low-dimensional coarse states, using an abstraction function.
result Achieves superhuman performance on Pitfall! and higher reward with fewer samples.

Private method measures nonlinear correlations between data hosted across two entities.

problem Measuring nonlinear correlations between sensitive data hosted across multiple parties while preserving privacy.
method Differentially private estimator of distance correlation.
result First private estimator of nonlinear correlations in a multi-party setup.

Paper uses RL to optimize insurance pricing on PCWs, improving efficiency and adaptability.

problem Optimizing pricing on price comparison websites while balancing competitiveness and profitability.
method Integrates model-based and model-free reinforcement learning methods for dynamic pricing.
result Hybrid RL agent outperforms existing methods in sample efficiency and cumulative reward.

Near-optimal private tests for simple and MLR hypotheses developed under Gaussian differential privacy.

problem Developing private tests for simple and MLR hypotheses under Gaussian differential privacy.
method A private mean estimator with data-driven clamping bounds, constructing private test statistics.
result Private tests achieve the same asymptotic relative efficiency as non-private most powerful tests.

Public pretraining improves private model training even in extreme distribution shift scenarios.

problem Improving private model training accuracy in settings with large distribution shift.
method Empirical evaluation and theoretical explanation of public representations improving private training accuracy.
result Public representations can improve private training accuracy by up to 67% over private training from scratch in settings with large distribution shift.

Private learning of Gaussian Mixture Models without boundedness assumptions.

problem Private estimation of parameters of Gaussian Mixture Models with unbounded components.
method Reduction to non-private problem, blackbox privatization, Moitra and Valiant's algorithm.
result First sample complexity upper bound and polynomial time algorithm for privately learning GMMs.

Algorithm selects public datasets for private machine learning.

problem Choosing the most suitable public dataset for private machine learning.
method Measures gradient subspace distance between public and private datasets.
result Excess risk scales with the subspace distance between gradients.

Differentially private hyperparameter tuning improves privacy in machine learning.

problem Hyperparameter tuning leaks private information through selected configurations.
method Local Bayesian optimization using Gaussian Process surrogate for private gradient approximation.
result DP-GIBO converges to locally optimal hyperparameters with polynomial dimensional dependence.

We consider learning problems where the training set consists of two types of examples: private and public. The goal is to design a learning algorithm that satisfies differential privacy only with respect to the private examples. This setting interpolates between private learning (where all examples are private) and cl…

2019-10-25abs ↗pdf ↗

Private distribution learning with public data, leveraging sample compression schemes.

problem Private distribution learning with public and private samples under differential privacy constraints.
method Connection to sample compression schemes and list learning.
result At least d public samples are necessary for private learnability of Gaussians in R^d.

In recent years, the economic policy of privatization, which is defined as the transfer of property or responsibility from public sector to private sector, is one of the global phenomenon that increases use of markets to allocate resources. One important motivation for privatization is to help develop factor and produc…

2008-03-17abs ↗pdf ↗

New private learning algorithms improve utility in tasks with public features.

problem Private learning with public features in recommendation and ad prediction.
method Developed algorithms that protect only certain sufficient statistics, improving utility for linear regression and private recommendation benchmarks.
result Achieved state-of-the-art performance on private recommendation benchmarks.

Improved differentially private deep learning with group-wise clipping techniques.

problem Efficiency and privacy trade-offs in deep learning models.
method Group-wise clipping techniques (per-layer and per-device) to reduce compute time and memory overhead.
result Private learning with group-wise clipping achieves similar or better performance than non-private learning with less wall time.

Private learning can perform well in high dimensions, contrary to known results.

problem When does differentially private learning not suffer in high dimensions?
method Introduced a condition called restricted Lipschitz continuity to derive improved bounds for excess empirical and population risks.
result Gradients in private fine-tuning of large models are mostly controlled by a few principal components, similar to conditions for convex settings.

New method for private density estimation of high-dimensional Gaussian mixtures.

problem Private density estimation for mixtures of unrestricted high-dimensional Gaussians.
method Exploits list global stability to prove upper bound on sample complexity.
result First upper bound on sample complexity for agnostic private density estimation.

Private algorithms adapt from public to private domains with minimal labeled data.

problem Adapting from a public source domain to a private target domain with few labeled data.
method Differentially private discrepancy minimization algorithms based on Frank-Wolfe and Mirror-Descent methods.
result Effective adaptation with strong generalization and privacy guarantees.

We study the sample complexity of private synthetic data generation over an unbounded sized class of statistical queries, and show that any class that is privately proper PAC learnable admits a private synthetic data generator (perhaps non-efficient). Previous work on synthetic data generators focused on the case that …

2019-02-09abs ↗pdf ↗

Private credit markets have expanded significantly, offering unique lending technology to private equity firms.

problem Understanding the growth and characteristics of private credit markets.
method Systematic survey of academic literature, development of integrated theoretical framework, empirical evidence.
result Private credit markets offer a distinct lending technology with higher spreads over syndicated loans.

We revisit the problem of differentially private release of classification queries. In this problem, the goal is to design an algorithm that can accurately answer a sequence of classification queries based on a private training set while ensuring differential privacy. We formally study this problem in the agnostic PAC …

2019-07-31abs ↗pdf ↗