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

207414620827 · Jun 202019922001200920172026
48 results for optimal learner

The paper addresses learner privacy in convex optimization with feedback.

problem Privacy risks from eavesdropping adversaries observing learner's queries.
method Optimally obfuscating learner's queries to make their learned optimal value hard to estimate.
result Query complexity overhead is additive in LL in the minimax formulation, multiplicative in LL in the Bayesian formulation.

We consider a multiobjective multiarmed bandit problem with lexicographically ordered objectives. In this problem, the goal of the learner is to select arms that are lexicographic optimal as much as possible without knowing the arm reward distributions beforehand. We capture this goal by defining a multidimensional for…

2019-07-26abs ↗pdf ↗

Deep reinforcement learning finds optimal learning policies for adaptive systems.

problem Finding individualized learning plans for learners with unknown latent traits.
method Formulated as a Markov decision process, applied deep Q-learning with a transition model estimator.
result The algorithm efficiently discovers optimal learning policies with small data sets.

Study compares methods for treatment assignment, finding A-learner best for playlist generation.

problem Treatment assignment in various applications.
method Three classes of algorithms: O-learner, E-learner, A-learner.
result Optimizing for outcomes or causal effects does not lead to optimal treatment assignments.

Machine teaching addresses the problem of finding the best training data that can guide a learning algorithm to a target model with minimal effort. In conventional settings, a teacher provides data that are consistent with the true data distribution. However, for sequential learners which actively choose their queries,…

2018-09-08abs ↗pdf ↗

Proof shows imitation of expert's reward and solutions in multi-objective optimization.

problem Multi-objective optimization with reward and solution imitation.
method Wasserstein inverse reinforcement learning.
result Wasserstein inverse reinforcement learning enables imitation of expert's reward and solutions in multi-objective optimization.

This paper analyzes the difficulty of unsupervised domain adaptation using information theory.

problem The challenge of unsupervised domain adaptation under covariate shift.
method Formulates the problem using a distribution π in the ground-truth triples (p, q, f), defines optimal learner performance, and introduces PTLU for quantifying difficulty.
result Characterizes the optimal learner and introduces PTLU as a measure of UDA difficulty.

New binary classification techniques help multiclass classification by aggregating proper learners.

problem Multiclass classification faces a properness barrier that prevents optimal learning by proper learners.
method Aggregations of proper binary learners, generalized to multiclass settings, achieve optimal sample complexity.
result Optimal binary learners can achieve sample complexity $O\left(\frac{d_G + \ln(1 / δ)}ε ight)$ for classes with finite Graph dimension dGd_G.

The paper presents a method for personalized exercise recommendations that improves learner skill gain.

problem Adapting to individual needs in large, diverse groups of learners in digital environments.
method Contextual Thompson Sampling to select exercises that advance learner skill.
result The method recommends exercises associated with greater skill improvement and adapts to learner differences.

Deep reinforcement learning algorithms have been successfully applied to a range of challenging control tasks. However, these methods typically struggle with achieving effective exploration and are extremely sensitive to the choice of hyperparameters. One reason is that most approaches use a noisy version of their oper…

2019-05-02abs ↗pdf ↗

Paper introduces GDR-learners for estimating potential outcomes from observational data.

problem Lack of theoretical property of general Neyman-orthogonality in deep generative models.
method Develops flexible GDR-learners based on various deep generative models.
result GDR-learners possess quasi-oracle efficiency and rate double robustness, asymptotically optimal.

F-PACOH improves meta-learners' reliability in uncertain regions.

problem Overconfident uncertainty estimates in meta-learning.
method Meta-learning priors as stochastic processes in function space, directly steering predictions towards high epistemic uncertainty.
result Significantly outperforms other meta-learners in Bayesian Optimization.

Meta-learning is a tool that allows us to build sample-efficient learning systems. Here we show that, once meta-trained, LSTM Meta-Learners aren't just faster learners than their sample-inefficient deep learning (DL) and reinforcement learning (RL) brethren, but that they actually pursue fundamentally different learnin…

2019-05-03abs ↗pdf ↗

Study the tradeoffs of bandit feedback in multiclass classification.

problem The price of using bandit feedback in multiclass classification.
method Mistake bound model, analysis of variants, and comparison of learners and adversaries.
result The optimal mistake bound under bandit feedback is at most O(k)O(k) times higher than in full information, with a tight bound of O(k)O(k).

We study the problem of online learning with non-convex losses, where the learner has access to an offline optimization oracle. We show that the classical Follow the Perturbed Leader (FTPL) algorithm achieves optimal regret rate of O(T1/2)O(T^{-1/2}) in this setting. This improves upon the previous best-known regret rate of…

2019-03-19abs ↗pdf ↗

Paper explores generalization of minimax learners, proposing a new metric.

problem Understanding how minimax learners perform on unseen data.
method Proposes a new metric, the primal gap, to study generalization of minimax learners.
result Derives generalization error bounds for the primal gap in nonconvex-concave settings.

This paper optimizes attacks on stochastic bandits and proposes defenses against them.

problem Optimizing adversarial attacks on stochastic bandit algorithms.
method Designs optimal attack strategies and proposes defense algorithms.
result Optimal attack strategies and defense algorithms achieve near perfect performance.

Meta-learning can successfully acquire useful inductive biases from data. Yet, its generalization properties to unseen learning tasks are poorly understood. Particularly if the number of meta-training tasks is small, this raises concerns about overfitting. We provide a theoretical analysis using the PAC-Bayesian framew…

2020-02-13abs ↗pdf ↗

We study a security threat to batch reinforcement learning and control where the attacker aims to poison the learned policy. The victim is a reinforcement learner / controller which first estimates the dynamics and the rewards from a batch data set, and then solves for the optimal policy with respect to the estimates. …

2019-10-13abs ↗pdf ↗

Boosting improves accuracy by combining weak learners into a voting classifier.

problem Boosting's theoretical performance is sub-optimal, especially for voting classifiers.
method Proposes a randomized boosting algorithm that outputs voting classifiers with a single logarithmic dependency on sample size.
result Randomized boosting achieves a generalization error with a single logarithmic dependency on the sample size.

Study best arm identification with limited precision sampling in bandits.

problem Limited precision sampling in multi-armed bandit problems.
method Proposed a modified tracking-based algorithm to handle non-unique optimal allocations and presented non-asymptotic bounds.
result Asymptotically optimal tracking-based algorithm for best arm identification.

A new meta-learner improves prediction of individualized outcomes in sequential decisions.

problem Predicting individualized outcomes over long horizons in sequential decision-making.
method Developed a novel meta-learner called DRQ-learner with theoretical guarantees of orthogonality and quasi-oracle efficiency.
result DRQ-learner achieves quasi-oracle efficiency, doubly robustness, and Neyman-orthogonality.

Robust X-Learner improves HTE estimation in imbalanced and heavy-tailed data.

problem Estimating HTE in imbalanced and heavy-tailed data.
method Integrates γ-divergence objective and Proxy Hessian strategy into gradient boosting.
result Reduces PEHE metric by 98.6% in semi-synthetic Criteo Uplift dataset.

New algorithm optimally identifies best arm in both stochastic and adversarial settings.

problem Best arm identification in stochastic and adversarial reward scenarios.
method Parameter-free algorithm designed to be robust to adversarial rewards and optimal in stochastic problems.
result Algorithm's error rate matches optimal bounds in stochastic problems and is robust to adversarial rewards.

Machine learning improves learning and memory retention by optimizing study sessions.

problem Improving learning and memory retention methods for factual material.
method Large-scale randomized controlled trial with machine learning optimization of study sessions.
result Study sessions optimized with machine learning lead to 67% longer retention and 50% higher return rate.

A meta-model is trained on a distribution of similar tasks such that it learns an algorithm that can quickly adapt to a novel task with only a handful of labeled examples. Most of current meta-learning methods assume that the meta-training set consists of relevant tasks sampled from a single distribution. In practice, …

2019-04-11abs ↗pdf ↗

This work introduces a transformation-based learner model for classification forests. The weak learner at each split node plays a crucial role in a classification tree. We propose to optimize the splitting objective by learning a linear transformation on subspaces using nuclear norm as the optimization criteria. The le…

2013-12-19abs ↗pdf ↗

New method efficiently evaluates policies using trajectory data.

problem Statistically efficient policy evaluation with limited data.
method Trajectory-based approach for policy evaluation.
result Improved sample complexity for policy evaluation.

Algorithm improves RL model selection for repeated games with utility maximization.

problem Optimal policy learning in repeated games with unknown opponent strategy.
method Proposes MRBEAR for average reward RL, applying to utility maximization in repeated games.
result Regret bound shows linear dependence on number of model classes in average reward RL.

We formulate a private learning model to study an intrinsic tradeoff between privacy and query complexity in sequential learning. Our model involves a learner who aims to determine a scalar value, vv^*, by sequentially querying an external database and receiving binary responses. In the meantime, an adversary observes…

2018-05-06abs ↗pdf ↗

We study a variant of decision-theoretic online learning in which the set of experts that are available to Learner can shrink over time. This is a restricted version of the well-studied sleeping experts problem, itself a generalization of the fundamental game of prediction with expert advice. Similar to many works in t…

2019-10-29abs ↗pdf ↗

Online learners track optimal solutions with constant step-size.

problem Tracking optimal solutions in online learning settings.
method Established a link between steady-state performance and tracking performance using analogies with adaptive filters.
result Inferred tracking performance from steady-state expressions directly.