Oracle-efficient algorithms for online learning with smoothed and hint-adversaries.
problem Online learning with beyond worst-case adversaries.
method Oracle-efficient algorithms for two settings: smoothed analysis and K K K -hint transductive learning. result Oracle-efficient regret bounds for learning real-valued and binary-valued functions.
New algorithms adapt to friendly environments in online learning.
problem Oracle-efficient algorithms struggle with friendly environments.
method Follow-the-perturbed-leader algorithms with approximability condition.
result Best-of-both-worlds bound in oracle-efficient setting.
New algorithms reduce reinforcement learning regret in factored MDPs.
problem Optimizing reinforcement learning in non-episodic factored MDPs.
method Proposed two near-optimal and oracle-efficient algorithms for FMDPs.
result Oracle-efficient algorithms achieve near-optimal regret bounds of O ( D S A T ) O(DS\sqrt{AT}) O ( D S A T ) . Oracle-efficient algorithms reduce combinatorial semi-bandit regret to logarithmic time.
problem Scalability issue in combinatorial semi-bandit problems due to high combinatorial optimization costs.
method Oracle-efficient frameworks that minimize oracle queries while maintaining tight regret guarantees.
result Achieved i l d e O ( T ) ilde{O}(\sqrt{T}) i l d e O ( T ) regret with O ( log log T ) O(\log\log T) O ( log log T ) oracle queries for worst-case linear rewards. New algorithm for online omniprediction with strong guarantees for continuous hypothesis classes.
problem Online adversarial learning with continuous hypothesis classes.
method Developed an oracle-efficient online multicalibration algorithm for infinite benchmark classes.
result First efficient online omnipredictor with strong guarantees for Lipschitz convex loss functions.
Three new oracle-efficient algorithms for private synthetic data release.
problem Constructing private synthetic data that preserves statistical query answers.
method Oracle-efficient algorithms using optimization oracles for differential privacy.
result Better accuracy in large workload and high privacy regime compared to state-of-the-art.
GPE algorithm optimizes nonparametric contextual bandits with efficient regret bounds.
problem Optimizing nonparametric contextual bandits with efficient regret bounds.
method Inspired by Policy Elimination, GPE uses oracle-efficient techniques for nonparametric classes with infinite VC-dimension.
result GPE is regret-optimal for policy classes with integrable entropy, and for larger entropy, it provides an ε \varepsilon ε -greedy algorithm with matching regret bounds. Oracle-efficient algorithm for offline RL with partial data coverage.
problem Offline reinforcement learning with partial data coverage and constraints.
method PDOCRL, a primal-dual algorithm with decomposed linear-programming formulation.
result Near-optimal, near-feasible policy with \(\widetilde{\mathcal O}(ε^{-2})\) sample guarantee.
New algorithms achieve small prediction regret for learning from overlapping groups.
problem Online multi-group learning with fairness applications.
method Oracle-efficient algorithms for groups not explicitly enumerated.
result Sublinear regret in various settings.
Improved algorithm for contextual bandits with reduced regret.
problem Adversarial contextual bandits with i.i.d. contexts.
method Oracle-efficient relaxation with O ( T 2 3 ( K log ( ∣ Π ∣ ) ) 1 3 ) O(T^{\frac{2}{3}}(K\log(|Π|))^{\frac{1}{3}}) O ( T 3 2 ( K log ( ∣Π∣ ) ) 3 1 ) regret bound. result First to improve regret bound and match original bound for stochastic case.
New algorithm achieves faster multicalibration in online settings.
problem Achieving fair predictions in online settings with limited interaction.
method Generalized multicalibration to arbitrary bounded hypothesis classes and introduced swap multicalibration. Proposed an oracle-efficient algorithm achieving faster multicalibration error.
result Oracle-efficient algorithm achieves T 1 / ( r + 1 ) T^{1/(r+1)} T 1/ ( r + 1 ) ℓ r \ell_r ℓ r -swap multicalibration error with high probability, improving on previous bounds. New algorithm tackles smooth online learning with optimal regret.
problem Smoothed online learning with adversarial distributions.
method Oracle-efficient algorithms for nonparametric function classes.
result Oracle-efficient algorithms achieve optimal regret bounds.
The paper addresses fairness in online learning by extending auditing schemes and presenting efficient algorithms.
problem Ensuring fairness in online learning while maximizing predictive accuracy.
method Extending auditing schemes to handle multiple auditors and presenting oracle-efficient algorithms.
result Presented algorithms achieve upper bounds on regret and fairness violations, improving on existing bounds.
New algorithms improve contextual bandit performance by adapting to problem difficulty.
problem Improving contextual bandit performance on problems with varying difficulty.
method Introducing complexity measures and oracle-efficient algorithms.
result Achieves optimal instance-dependent regret bounds for rich policy classes.
New algorithm reduces online learning error for unknown feature distributions.
problem Oracle-efficient hybrid online learning with unknown feature and label distributions.
method Computational efficient online predictor using ERM oracle for finite-VC and fat-shattering classes.
result Oracle-efficient sublinear regret bounds for hybrid online learning with unknown feature generation.
New algorithm achieves small-loss bounds in online learning with improved rates.
problem Achieving strong stability in online learning algorithms.
method Introduces ρ ρ ρ -separation to enforce strong stability, unifying previous approaches. result Oracle-efficient algorithm achieves small-loss bounds with improved rates.
One of the most effective algorithms for differentially private learning and optimization is objective perturbation. This technique augments a given optimization problem (e.g. deriving from an ERM problem) with a random linear term, and then exactly solves it. However, to date, analyses of this approach crucially rely …
Paper addresses hybrid learning with constrained adversaries, achieving optimal performance.
problem Hybrid learning problem with i.i.d. features and adversarial labels.
method Structured adversarial setting, efficient algorithm with ERM oracle.
result Oracle-efficient algorithm with regret scaling with Rademacher complexity.
We develop theory for using heuristics to solve computationally hard problems in differential privacy. Heuristic approaches have enjoyed tremendous success in machine learning, for which performance can be empirically evaluated. However, privacy guarantees cannot be evaluated empirically, and must be proven --- without…
EP-learning framework improves causal contrast estimation efficiency.
problem Estimating heterogeneous causal contrasts efficiently and stably.
method EP-learning framework combining T-learning and DR-learning.
result EP-learners are oracle-efficient and outperform competitors.
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 ( l o g ( T ) ) O(log(T)) O ( l o g ( T )) offline oracle calls. 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 ) O(\log T) O ( log T ) calls to an offline regression oracle. New framework converts offline to online estimation using black-box offline estimators.
problem Convert offline estimation algorithms to online estimation algorithms.
method Oracle-Efficient Online Estimation (OEOE) framework.
result Achieves near-optimal online estimation error via black-box offline estimators.
We study the computational tractability of PAC reinforcement learning with rich observations. We present new provably sample-efficient algorithms for environments with deterministic hidden state dynamics and stochastic rich observations. These methods operate in an oracle model of computation -- accessing policy and va…
Algorithm POLO learns low-rank MDPs with adversarial changes in full-info feedback.
problem Learning low-rank MDPs with adversarial changes and unknown transition probabilities.
method Policy optimization-based algorithm POLO with regret guarantee.
result POLO achieves sublinear regret guarantee with no dependence on state space size.
New algorithm learns efficiently with a simple 'yes/no' oracle.
problem Can efficient learning be achieved with a simpler oracle than ERM?
method Developed an oracle that returns 'yes' or 'no' for realizable datasets.
result Learnability is possible with a polynomial price in VC dimension.
Study efficient auditing of ML fairness models.
problem Scalability of auditing ML models for fairness.
method Query-based auditing algorithms for estimating demographic parity.
result Optimal deterministic and practical randomized algorithms for fairness estimation.
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.
Boosts barely robust learners to be more adversarially robust.
problem Learning predictors robust to small perturbations on a small fraction of data.
method Oracle-efficient algorithm for robustness with larger perturbation set.
result Qualitative and quantitative equivalence between strongly robust and barely robust learning.
Paper proposes a method to efficiently estimate structural breaks in cointegrating regressions.
problem Estimating structural breaks in cointegrating regressions is challenging due to inconsistency of group lasso.
method Adaptive group lasso procedure using a first step group lasso estimation of diverging breakpoint candidates to produce weights for a second estimation.
result The adaptive group lasso estimator delivers consistent parameter changes and oracle properties.
New algorithm learns FMDP structure while minimizing regret.
problem Regret minimization in FMDPs with unknown structure.
method Optimism in face of uncertainty principle combined with statistical structure learning.
result First algorithm to learn FMDP structure while minimizing regret.
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.
We consider settings in which the right notion of fairness is not captured by simple mathematical definitions (such as equality of error rates across groups), but might be more complex and nuanced and thus require elicitation from individual or collective stakeholders. We introduce a framework in which pairs of individ…
The paper addresses bias in survival analysis due to informative censoring.
problem Bias in treatment effect estimates due to informative censoring in survival analysis.
method Assumption-lean framework using partial identification to derive bounds on CATE.
result Proposes a meta-learner, SurvB-learner, to estimate bounds on CATE.
New methods for estimating treatment effects with missing data.
problem Missing outcome data complicates estimating treatment effects.
method Proposed two de-biased machine learning estimators (mDR-learner and mEP-learner) to address under-representation.
result Oracle efficiency of the proposed estimators under reasonable conditions.
We study an online classification problem with partial feedback in which individuals arrive one at a time from a fixed but unknown distribution, and must be classified as positive or negative. Our algorithm only observes the true label of an individual if they are given a positive classification. This setting captures …
We investigate two perturbation approaches to overcome conservatism that optimism based algorithms chronically suffer from in practice. The first approach replaces optimism with a simple randomization when using confidence sets. The second one adds random perturbations to its current estimate before maximizing the expe…
We propose a new family of fairness definitions for classification problems that combine some of the best properties of both statistical and individual notions of fairness. We posit not only a distribution over individuals, but also a distribution over (or collection of) classification tasks. We then ask that standard …
Efficiently learns private models using public data.
problem Improving private learning performance with public data.
method Proves computationally efficient algorithms for private learning with public data.
result First computationally efficient algorithms for private learning with public data.
New algorithms adapt to model misspecification in contextual bandits.
problem Design efficient algorithms for contextual bandits that handle model misspecification gracefully.
method Oracle-efficient algorithms for ε-misspecified contextual bandits using square loss regression.
result First algorithm achieving optimal regret bound for unknown misspecification level in linear contextual bandits.
Efficient algorithm for CMDPs reduces to offline density estimation.
problem Offline learning for CMDPs with horizon H.
method Reduction to offline density estimation, layerwise exploration-exploitation tradeoff.
result First efficient and near-optimal reduction from CMDPs to offline density estimation.
Algorithm identifies best arm in combinatorial bandits with semi-bandit feedback.
problem Identifying the best arm in combinatorial bandits with semi-bandit feedback.
method Interpreted as a sequential zero-sum game, developed a CombGame meta-algorithm with finite time guarantees.
result First computationally efficient algorithm that is asymptotically optimal and has competitive empirical performance.
New algorithm reduces regret in online learning for piecewise continuous functions.
problem Exponential loss in efficiency when moving from classical to adversarial learning.
method Introduces generalized bracketing numbers and Follow-the-Perturbed-Leader algorithm.
result Optimal scaling of optimization oracle calls with average regret.
New algorithm reduces sample complexity for multi-distribution learning.
problem Achieving data-efficient multi-distribution learning with robustness and fairness.
method Proposes a novel algorithm with sample complexity (d+k)/varepsilon^2 for Vapnik-Chervonenkis (VC) dimension d, matching lower bounds.
result Algorithm matches best-known lower bound and resolves open problems in COLT 2023.
Motivated by settings in which predictive models may be required to be non-discriminatory with respect to certain attributes (such as race), but even collecting the sensitive attribute may be forbidden or restricted, we initiate the study of fair learning under the constraint of differential privacy. We design two lear…
Near-optimal algorithms for predicting across multiple loss functions efficiently.
problem Predicting optimally across various loss functions simultaneously.
method Developed near-optimal online and offline learning algorithms for omniprediction.
result Achieved near-optimal complexity for both online and offline settings.
Papers learn from data to make decisions without interacting, improving on previous methods.
problem Achieving optimal decision-making from offline data with non-linear function approximation.
method Pessimistic Nonlinear Least-Square Value Iteration (PNLSVI) with three innovative components.
result Achieves minimax optimal instance-dependent regret for non-linear function approximation.
RichID learns optimal control policies from nonlinear observations.
problem Continuous control with unknown nonlinearity in system model.
method RichID algorithm using a least-squares regression oracle.
result First provable sample complexity guarantee for continuous control.