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.

168,694 papers · 148 categories

Trend · papers per month

132264395527 · Jun 202019922001200920172026
48 results for Multiple logging policies

Paper finds efficient OPE estimator for multiple logging policies with minimum variance.

problem Finding optimal importance sampling weights for multiple logging policies with varying variances.
method Established efficiency bound under stratified sampling and proposed an estimator achieving this bound.
result Proposed estimator achieves minimum variance for any instance.

Industrial recommender systems deal with extremely large action spaces -- many millions of items to recommend. Moreover, they need to serve billions of users, who are unique at any point in time, making a complex user state space. Luckily, huge quantities of logged implicit feedback (e.g., user clicks, dwell time) are …

2018-12-06abs ↗pdf ↗

DOLCE improves off-policy evaluation and learning by decomposing effects.

problem Bias in off-policy evaluation and learning due to policy mismatch.
method Uses lagged contexts and a moment-based training procedure to decompose and cancel bias.
result DOLCE achieves substantial improvements in off-policy evaluation and learning.

Study on sample complexity of policy gradient for stabilizing linear systems under multiplicative noise.

problem Learning optimal feedback gain for stabilizing linear systems with multiplicative noise.
method Analyzes the sample complexity of policy gradient methods, addressing the cusp obstruction and using symmetry to control divergent parts of the gradient.
result Proves that projected mini-batch policy gradient attains total sample complexity of O(1/η) when noise density is known and O(η^(-(2s+1)/(2s))) when estimated, for C^s noise densities with s ≥ 2.

Paper proposes a framework for reliable off-policy evaluation in reinforcement learning.

problem Quantifying uncertainty in off-policy estimates for safe deployment of target policies.
method Distributionally robust optimization for creating confidence bounds.
result Non-asymptotic and asymptotic guarantees for robust cumulative reward estimates.

Develops a support-aware framework for reserve-policy selection in advertising markets.

problem Log-based reserve-price evaluation risks weak support and subgroup harm.
method Support-aware offline decision framework converting logged evidence into certified policies.
result Preserves the best gate-passing policy while eliminating only policies with certified regret.

It is well known that the historical logs are used for evaluating and learning policies in interactive systems, e.g. recommendation, search, and online advertising. Since direct online policy learning usually harms user experiences, it is more crucial to apply off-policy learning in real-world applications instead. Tho…

2019-07-23abs ↗pdf ↗

A new estimator for evaluating policies in unknown environments.

problem Evaluating policies when both logging policy and value function are unknown.
method Doubly-Robust (DR) off-policy evaluation (OPE) estimator, DRUnknown, that estimates both the logging policy and value function.
result DRUnknown achieves the smallest asymptotic variance and is optimal when both models are correctly specified.

The paper tackles counterfactual learning for stochastic policies with continuous actions.

problem Learning stochastic policies with continuous actions from logged data.
method Introduces a joint kernel embedding of contexts and actions to model continuous actions, and uses proximal point algorithms and smooth estimators for optimization.
result Demonstrates the benefits of using proximal point algorithms and smooth estimators for counterfactual learning.

Develops an anytime-valid framework for optimal policy identification from logged contextual bandit data.

problem Selecting the optimal policy from a candidate policy class while monitoring evidence continuously.
method Constructs a time-indexed set that retains the true optimal policy set uniformly over time.
result The procedure allows the analyst to monitor policy values, eliminate clearly suboptimal policies, and stop at data-dependent times without invalidating inference.

Proposes log density gradient to improve reinforcement learning sample complexity.

problem Residual error in gradient estimation in policy gradient methods.
method Log density gradient method to correct residual error, using state-action discounted distributional formulation.
result Min-max optimization method to approximate log density gradient with on-policy samples, achieving sample complexity of m1/2m^{-1/2}.

Two algorithms achieve optimal regret with limited adaptivity in multinomial logistic bandits.

problem Achieving optimal regret with limited adaptivity in multinomial logistic bandits.
method Presented two algorithms, B-MNL-CB and RS-MNL, for batched and rarely-switching paradigms.
result Achieved ildeO(T) ilde{O}(\sqrt{T}) regret with limited adaptivity.

New algorithm tackles dynamic query routing to multiple embedding models.

problem Dynamic query routing to multiple embedding models under adversarial conditions.
method Formalized as adversarial contextual linear bandit with low-rank experts, proposed HPG algorithm.
result HPG algorithm achieves linearized policy regret of ildeO(sMT) ilde{\mathcal O}(s\sqrt{M T}).

A new method for evaluating and selecting policies in contextual bandits improves confidence intervals and policy quality.

problem Evaluating and selecting policies in contextual bandits with logged data.
method Self-normalized Importance Weighting (SN) estimator with Efron-Stein tail inequality and multiplicative bias control.
result The method provides tighter confidence intervals and better policy selection compared to competitors.

A new method combines online and offline learning to tackle contextual bandits with missing action support.

problem Learning optimal policies with logged data when the logging policy has deficient support.
method Hybrid approach using online exploration to exploit supported actions and offline learning to avoid unnecessary explorations.
result Determines an optimal policy with theoretical guarantees using minimal online explorations.

Study on policy gradient for stochastic bandits using diffusion approximation.

problem Improving policy gradient methods for stochastic bandits with optimal regret bounds.
method Continuous-time diffusion approximation of policy gradient with learning rate analysis.
result Proved optimal regret bound of O(klog(k)log(n)/η)O(k \log(k) \log(n) / η) for η=O(Δ2/log(n))η= O(Δ^2/\log(n)).

Novel LSE estimator improves off-policy learning and evaluation.

problem High variance and poor performance with low-quality propensity scores and heavy-tailed reward distributions.
method Introduces a novel estimator based on the log-sum-exponential (LSE) operator.
result Achieves convergence rate of O(nε/(1+ε))O(n^{-ε/(1+ ε)}) for regret bounds.

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.

Paper proposes a new DR estimator for adaptive experiments with improved performance.

problem Improving policy evaluation in adaptive experiments with dependent samples.
method Adaptive-fitting variant of sample-splitting for non-Donsker nuisance estimators.
result Proposed DR estimator shows better performance than other estimators with dependent samples.

We consider active learning with logged data, where labeled examples are drawn conditioned on a predetermined logging policy, and the goal is to learn a classifier on the entire population, not just conditioned on the logging policy. Prior work addresses this problem either when only logged data is available, or purely…

2018-02-25abs ↗pdf ↗

New loss functions optimize pricing policies using transaction data, ensuring expected revenue guarantees.

problem Optimizing pricing policies with transaction data where valuation data is not directly observed.
method Introducing convex loss functions for contextual pricing, focusing on log-concave valuation distributions.
result Proved expected revenue bounds for generalized hinge and quantile pricing loss functions.

Study improves unbiased recommender learning by addressing missing-reward bias.

problem Data bias caused by missing-reward observations in recommender systems.
method Proposes a novel estimator using propensity scores to mitigate both position and reward bias.
result The proposed estimator outperforms other methods, even with increased reward observation bias.

New RL algorithm reduces policy switching cost to loglog(T) with similar regret.

problem Low policy switching cost in real-life RL applications.
method Stage-wise exploration and adaptive policy elimination.
result Regret of O(HSAloglogT)O(HSA \log\log T) with O(HSAloglogT)O(HSA \log\log T) switching cost.

New estimator reduces risk in slate bandits by leveraging Bayes risk criterion.

problem Evaluating slate policies using logged data when policies factorize over slots.
method Developed a new estimator using a control variate approach, showing risk improvement over existing methods.
result The new estimator has lower risk than the pseudoinverse estimator in slate bandit problems.

New estimator uses clustering to improve off-policy evaluation accuracy.

problem Improving off-policy evaluation accuracy when logging and evaluation policies differ.
method Proposes an estimator that shares information across similar contexts using clustering.
result Clustering contexts improves estimation accuracy, especially in deficient information settings.

Study nonparametric estimator for Markov chain transition matrices in offline setting.

problem Estimating transition matrices of finite controlled Markov chains from logged data.
method Developed sample complexity bounds and conditions for minimaxity.
result Achieving certain statistical risk requires balancing mixing properties and sample size.

Develops CLTs for Markov chain transition probabilities and policies.

problem Estimating transition probabilities and policies in controlled Markov chains.
method Non-parametric estimator for transition matrices; CLTs for value, Q-, and advantage functions; goodness-of-fit tests.
result Asymptotic normality of estimators under specific logging policies.

Log-Normal Multiplicative Dynamics improves low-precision training of neural networks.

problem Training large neural networks with low precision is unstable.
method Derive a Bayesian learning rule with log-normal posterior distributions and multiplicative updates.
result LMD achieves stable and accurate training for Vision Transformer and GPT-2.

This work highlights problems with off-policy estimation in recommender systems due to unobserved confounders.

problem Evaluation of recommender systems under unobserved confounders.
method Policy-based estimators and characterisation of statistical bias due to confounding.
result Naive propensity estimation under confounding leads to severely biased metric estimates.

We devise and analyze algorithms for the empirical policy evaluation problem in reinforcement learning. Our algorithms explore backward from high-cost states to find high-value ones, in contrast to forward approaches that work forward from all states. While several papers have demonstrated the utility of backward explo…

2020-02-18abs ↗pdf ↗

Off-policy reinforcement learning (RL) using a fixed offline dataset of logged interactions is an important consideration in real world applications. This paper studies offline RL using the DQN replay dataset comprising the entire replay experience of a DQN agent on 60 Atari 2600 games. We demonstrate that recent off-p…

2019-07-10abs ↗pdf ↗

This work explores the idea of a causal contextual multi-armed bandit approach to automated marketing, where we estimate and optimize the causal (incremental) effects. Focusing on causal effect leads to better return on investment (ROI) by targeting only the persuadable customers who wouldn't have taken the action orga…

2018-10-02abs ↗pdf ↗

MAMBA learns policies competitive with multiple conflicting oracles.

problem Learning policies from multiple conflicting oracles in reinforcement learning.
method MAMBA uses a gradient estimator in the style of GAE to optimize policies, leveraging demonstrations from multiple weak oracles.
result MAMBA outperforms the state-of-the-art in learning policies competitive with multiple conflicting oracles.

The paper tackles robust policy learning from multiple data sources.

problem Learning a policy that generalizes across diverse settings from multiple heterogeneous data sources.
method Proposes a minimax regret optimization objective and a policy learning algorithm combining doubly robust offline policy evaluation and no-regret learning.
result Achieves minimal worst-case mixture regret up to a moderated vanishing rate of the total data across all sources.

Learning policies that generalize across multiple tasks is an important and challenging research topic in reinforcement learning and robotics. Training individual policies for every single potential task is often impractical, especially for continuous task variations, requiring more principled approaches to share and t…

2013-07-02abs ↗pdf ↗

wd1 improves reasoning in dLLMs by optimizing policies without policy ratios.

problem Improving reasoning in diffusion-based large language models through RL.
method wd1: ratio-free policy optimization using weighted log-likelihood.
result wd1 outperforms diffusion-based GRPO while requiring lower computational cost.