Algorithm solves online binary classification and infinite games using ERM oracle.
problem Online learning and solving infinite games with computationally inefficient oracles.
method Proposes an algorithm relying solely on ERM oracle calls for online binary classification and nonparametric games.
result Achieves finite and sublinearly growing regret in various settings.
New algorithms solve games to find optimal exploration strategies.
problem Sequentially gather information to answer queries about stochastic environments.
method Interpret optimisation problem as a game and use iterative strategies to estimate its saddle point.
result First finite confidence guarantees for pure exploration in exponential families.
Estimates heavy hitters in data streams with queries, balancing accuracy and efficiency.
problem Identifying elements with high probability in i.i.d. samples.
method Sequential estimation algorithms for two query models: index and pair queries.
result Upper and lower bounds on query complexity for different distributions and noise models.
New research shows fixed-budget best-arm identification cannot match static oracle performance.
problem Fixed-budget best-arm identification's performance limitations.
method Analysis of various adaptive and static algorithms for best-arm identification.
result For any algorithm, there exists at least one instance where the error decay rate is at most \((1 + \frac{\log(K)}{8})^{-1}\) times that of the static oracle.
Missing responses is a missing data format in which outcomes are not always observed. In this work we develop kernel machines that can handle missing responses. First, we propose a kernel machine family that uses mainly the complete cases. For the quadratic loss, we then propose a family of doubly-robust kernel machine…
The paper enhances preference learning by incorporating response time data.
problem Lack of temporal information in user decision-making for reward model learning.
method Integrates response time alongside binary choice data using the EZ model and Neyman-orthogonal loss functions.
result Response time-augmented approach reduces error rates from exponential to polynomial scaling, improving sample efficiency.
Pairwise "same-cluster" queries are one of the most widely used forms of supervision in semi-supervised clustering. However, it is impractical to ask human oracles to answer every query correctly. In this paper, we study the influence of allowing "not-sure" answers from a weak oracle and propose an effective algorithm …
Self-Tuning Networks optimize hyperparameters using bilevel optimization and gated best-response functions.
problem Optimizing hyperparameters for neural networks.
method Bilevel optimization with gated best-response functions to adapt regularization hyperparameters online.
result Self-Tuning Networks outperform fixed hyperparameter values on large-scale deep learning problems.
Improved FTPL algorithm reduces regret in predictable minimax games.
problem Online learning and minimax games with predictable loss sequences.
method Optimistic modification of FTPL with dual regularization view.
result Tighter regret bounds for predictable sequences, O(T−1/2) accuracy. Bayesian-guided method selects optimal design from large candidate pool.
problem Optimizing complex structures with high-fidelity evaluations.
method Bayesian active learning with surrogate modeling.
result Optimal design identified with minimal oracle evaluations.
Grover search for optimal portfolios based on Sharpe ratio.
problem Finding optimal portfolios with specific risk-return characteristics.
method Grover's algorithm applied to portfolio selection with oracles.
result Quantum algorithms can efficiently find optimal portfolios.
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.
Unified formulation bridges adversarial and nonstationary bandits.
problem Handling time-varying reward distributions in multi-armed bandit problems.
method Unified oracle that switches between adversarial and nonstationary bandit oracles based on window size.
result Optimal regret achieved with matching lower bound.
We revisit the question of reducing online learning to approximate optimization of the offline problem. In this setting, we give two algorithms with near-optimal performance in the full information setting: they guarantee optimal regret and require only poly-logarithmically many calls to the approximation oracle per it…
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.
Optimal adversarial noise algorithms for multiple classifiers using game theory.
problem Designing robust attacks against multiple classifiers.
method Formulating the problem as a two-player, zero-sum game and using Multiplicative Weights Update framework with best response oracles.
result Demonstrated the effectiveness of randomization in adversarial attacks and optimal mixed strategies.
Probabilistic Bisection Algorithm performs root finding based on knowledge acquired from noisy oracle responses. We consider the generalized PBA setting (G-PBA) where the statistical distribution of the oracle is unknown and location-dependent, so that model inference and Bayesian knowledge updating must be performed s…
We propose a method to extract interpretable rules from tree ensembles.
problem Tree ensembles are accurate but hard to interpret.
method Propose an estimator to extract compact sets of decision rules from tree ensembles.
result Our estimator improves accuracy and reveals useful relationships in the data.
New algorithm reduces high-dimensional data processing costs and achieves true sparsity.
problem High computational costs and difficulty in achieving true sparsity in distributed inference.
method Two-stage distributed best subset selection with oracle property.
result Correctly finds true sparsity pattern and achieves the oracle property.
New lower bounds for bilevel optimization with first-order oracles.
problem Complexity of bilevel optimization with first-order oracles.
method Development of hard instances and proof of lower bounds.
result Nontrivial lower bounds for first-order zero-respecting algorithms.
Develops shuffling gradient-based methods for nonconvex-concave minimax optimization.
problem Nonconvex-concave minimax optimization problems.
method Two shuffling gradient-based algorithms for nonconvex-linear and nonconvex-strongly concave settings.
result Achieves state-of-the-art oracle complexity in nonconvex optimization and best-known complexity bounds for nonconvex-strongly concave setting.
New algorithm finds best subset in high-dimensional data models.
problem Finding the best subset of predictors in high-dimensional data models.
method Proposes a scalable algorithm using a generalized information criterion.
result Directly proves consistency and oracle property for the best-subset selection.
New robust estimator for high-dimensional data with outliers and leverage points.
problem Robust regression in high-dimensional datasets with gross contamination.
method Adaptive τ-Lasso estimator with an adaptive ℓ1-norm penalty.
result Adaptive τ-Lasso has the oracle property and robustness to outliers and high-leverage points.
New algorithm reduces contextual bandit identification to argmax calls.
problem Best-arm identification in stochastic contextual bandits.
method Instance-optimal PAC algorithm using argmax oracle calls.
result First instance-dependent PAC sample complexity for contextual bandits.
Study best-response learning dynamics in zero-sum polymatrix games under full and minimal information settings.
problem Learning dynamics in zero-sum polymatrix games under different information settings.
method Two-timescale learning dynamics combining smoothed best-response updates and TD-learning for estimating local payoff functions.
result Polynomial-time finite-sample guarantees for convergence to an ε-Nash equilibrium in the minimal information case.
Two novel procedures track quantiles efficiently using an oracle.
problem Setting step size and tuning parameters for incremental quantile estimators.
method Estimate MSE, decompose into variance and bias, use oracle to select best estimator.
result Efficient quantile tracking with error close to theoretical optimum.
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-greedy algorithm with matching regret bounds. Feature interactions can contribute to a large proportion of variation in many prediction models. In the era of big data, the coexistence of high dimensionality in both responses and covariates poses unprecedented challenges in identifying important interactions. In this paper, we suggest a two-stage interaction identi…
Neural operators approximate Stackelberg game solutions.
problem Intractability of follower's best-response operator in dynamic Stackelberg games.
method Used attention-based neural operators to approximate the best-response operator.
result Approximate best-response operator yields close game value.
Two methods for model adaptation compared; fine-tuning outperforms Best-of-N in realizable settings.
problem Comparing methods for adapting large language models to new tasks.
method Supervised fine-tuning vs. Best-of-N approach.
result Supervised fine-tuning outperforms Best-of-N in realizable settings.
New method for sparse kernel selection improves prediction accuracy.
problem Sparse Multiple Kernel Learning for binary classification.
method Alternating best response algorithm with semidefinite relaxations.
result Method outperforms state-of-the-art MKL approaches in prediction accuracy.
Improved algorithm for contextual bandits with reduced regret.
problem Adversarial contextual bandits with i.i.d. contexts.
method Oracle-efficient relaxation with O(T32(Klog(∣Π∣))31) regret bound. result First to improve regret bound and match original bound for stochastic case.
Improved hypernetwork for efficient neural network hyperparameter tuning.
problem Efficiently optimizing hyperparameters in neural networks.
method Proposed Δ-STN architecture focusing on accurate best-response Jacobian approximation. result Significantly improved hyperparameter tuning accuracy and stability.
MELO predicts electricity loads by adapting to shifts without external indicators.
problem Adapting to non-stationary prediction challenges in online settings.
method MELO combines multiple forgetting factors and aggregation rules to adaptively predict.
result MELO reduces RMSE by 34.7% compared to base predictors and external covariates.
Paper introduces metrics for evaluating multi-agent policies using best response dynamics.
problem Evaluation and ranking of multi-agent policies in reinforcement learning.
method Adopting strict best response dynamics (SBRD) to model selfish behaviors, proposing perturbed SBRD for dynamic and non-stationary settings.
result Proposed perturbed SBRD can observe policies with maximum metrics and differ from optimal by any given tolerance.
New algorithms achieve decision calibration without sample complexity dependent on feature dimension.
problem Achieving decision calibration for nonlinear loss functions with polynomial sample complexity.
method Developed smooth relaxation of decision calibration, enabling dimension-free algorithms.
result Efficient algorithms post-process predictors to satisfy decision calibration without worsening accuracy.
Best-of-N sampling reveals reward targets from preference data, influencing N and base distribution choices.
problem Understanding reward extraction from Best-of-N preference data and optimal N and base distribution choices.
method Specialized analysis of preference data via induced conditional distribution, deriving reward targets and design principles.
result Reward targets are explicit functions of N and base distribution, and bounded-class minimizers approach these targets as N grows.
Minimax PAC bounds for learning in exogenous contextual MDPs
problem PAC learning in tabular discounted Markov decision processes with exogenous i.i.d. contexts
method Variance-reduced algorithm for policy evaluation, best-value estimation, and best-policy extraction
result Minimax optimal sample complexity
Propose an XMSE-aware mixed estimator for EB that interpolates between ML and EB shrinkage.
problem Kernel-based EB estimation may be worse than ML when the kernel is poorly aligned with the true parameter.
method An XMSE-aware mixed estimator that interpolates between ML and EB shrinkage.
result Fixed-weight XMSE is a scalar quadratic, yielding a closed-form oracle mixing weight that is no worse than both ML and the base EB estimator at the XMSE scale.
Algorithms for hyperparameter optimization abound, all of which work well under different and often unverifiable assumptions. Motivated by the general challenge of sequentially choosing which algorithm to use, we study the more specific task of choosing among distributions to use for random hyperparameter optimization.…
Paper studies zero-sum games with noisy observations and identifies equilibrium conditions.
problem Zero-sum games with noisy observations of the leader's actions.
method Analyzes the equilibrium of games with noisy action observability, identifies necessary conditions for uniqueness, and investigates the cardinality of best responses.
result The noisy observations significantly impact the cardinality of the follower's set of best responses, and under certain conditions, this set becomes a singleton almost surely.
Optimizes personalized medicine prediction by individual tuning.
problem Predicting individual drug responses using genomic information.
method Introduces a new ridge estimator and tuning parameter calibration scheme.
result Optimal in terms of oracle inequalities, fast, and highly effective.
New algorithms solve stochastic variational inequalities without bounded variance assumption.
problem Solving stochastic variational inequalities without bounded variance assumption.
method Developed algorithms for two classes of problems: monotone and structured nonmonotone VIs.
result Oracle complexity of O(ε^-4) for solving VIs with unbounded domains and possibly unbounded variance.
We present a new algorithm for the contextual bandit learning problem, where the learner repeatedly takes one of K actions in response to the observed context, and observes the reward only for that chosen action. Our method assumes access to an oracle for solving fully supervised cost-sensitive classification problem…
The paper proposes a framework for structured prediction using projection oracles.
problem Structured prediction with improved loss functions.
method A general framework for deriving loss functions using convex sets and projection oracles.
result Projections onto the marginal polytope can make the loss smaller and are computationally efficient.
We present a generic framework for trading off fidelity and cost in computing stochastic gradients when the costs of acquiring stochastic gradients of different quality are not known a priori. We consider a mini-batch oracle that distributes a limited query budget over a number of stochastic gradients and aggregates th…
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 algorithms ensure reproducibility and optimal convergence in convex optimization.
problem Trade-off between reproducibility and convergence rate in convex optimization.
method Regularization-based algorithms for smooth convex minimization and minimax optimization.
result Achieves optimal reproducibility and near-optimal gradient complexity for various oracle settings.