Paper studies how to cluster data with a weak oracle, reducing the number of queries needed.
problem Cluster data with limited oracle answers.
method Proposes algorithms for semi-supervised active clustering with weak oracles.
result Shows that a small number of queries is sufficient for effective clustering.
New research shows label refinement and weak training have limitations for aligning LLMs.
problem Limitations of refinement methods for aligning large language models.
method Analyzed probabilistic assumptions and alternative approaches to label refinement and weak training.
result Label refinement and weak training suffer from irreducible error, leaving a performance gap.
Paper proposes handling uncertainties in clustering supervision.
problem Ineffective human oracles in answering all clustering queries.
method Introduces weak oracles that can answer 'not sure' and proposes an algorithm to use these answers effectively.
result Small query complexity is sufficient for effective clustering with high probability.
Study on tradeoffs between mistakes and ERM oracle calls in online and transductive learning.
problem Analyzing online and transductive learning with limited ERM and weak consistency oracle access.
method Proves lower bounds and upper bounds on mistakes and oracle calls, considering realizable and agnostic cases.
result Achieves optimal mistake bounds with weak consistency queries for certain concept classes.
An algorithm learns from multiple models to match an oracle's risk.
problem Learning from multiple noisy models to estimate a target parameter.
method Elimination rounds algorithm for adaptive learning.
result Risk of weak-oracle learner matches that of an oracle in multiple source case.
New model for learning from noisy human comparisons, improving search efficiency.
problem Designing efficient algorithms for content search with noisy human feedback.
method Introducing a weak oracle model for comparison-based queries and developing WORCS-I and WORCS-II algorithms.
result Provable algorithms locating target objects with close to entropy of target distribution.
An active learner is given a hypothesis class, a large set of unlabeled examples and the ability to interactively query labels to an oracle of a subset of these examples; the goal of the learner is to learn a hypothesis in the class that fits the data well by making as few label queries as possible. This work addresses…
Estimates CATEs for structured treatments using a new decomposition method.
problem Estimating conditional average treatment effects for complex data types.
method Generalized Robinson decomposition, isolating causal estimand, arbitrary model plugging, quasi-oracle convergence guarantee.
result Demonstrates superior performance in CATE estimation compared to prior work.
Sparse-penalized deep neural networks improve performance in weakly dependent processes.
problem Nonparametric regression and classification under weak dependence.
method Sparse-penalized deep neural networks with oracle inequalities and convergence rates established.
result The proposed estimators outperform non-penalized ones in simulations.
Efficiently plans large MDPs with weak function approximations.
problem Planning in large MDPs with limited function approximation capabilities.
method Uses linear value function approximation with weak requirements and a generative oracle.
result Produces almost-optimal actions for any state with polynomial computation time.
Extracts fairness truth from classifiers using an oracle.
problem Fairness in classification algorithms without context.
method Uses fairness oracle to learn underlying fairness truth.
result Extracts metric fairness from classifiers.
Paper develops robust regression method for heavy-tailed errors.
problem High-dimensional robust regression with heavy-tailed errors.
method Iteratively reweighted ℓ 1 \ell_1 ℓ 1 -penalized adaptive Huber regression. result Oracle convergence rate and variable selection consistency achieved.
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.
New method improves IV estimation with many weak and invalid instruments.
problem Identification in linear IV models with unknown validity.
method Non-convex penalized approaches, surrogate sparsest penalty.
result Advantages over other IV estimators in selection consistency and weak IV strength conditions.
Paper proposes estimators for sparse PCA with oracle property.
problem Estimating sparse principal subspace in high-dimensional settings.
method Semidefinite relaxation with novel regularizations.
result One estimator achieves exact support recovery and statistical rate.
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.
Paper tackles noisy comparison oracle for robust clustering algorithms.
problem Finding robust clustering algorithms under noisy comparison oracle.
method Develops algorithms for k-center clustering and agglomerative hierarchical clustering using noisy comparison oracle.
result Proves robust algorithms achieve good approximation guarantees with high probability.
Interactive weak supervision learns useful heuristics from user feedback.
problem Creating useful heuristics for large labeled datasets is tedious and subjective.
method Develops an interactive framework for learning heuristics from user feedback.
result Only a few feedback iterations are needed to train models without ground truth labels.
The paper improves NBR for count data using elastic-net regularization, achieving consistency and weak signal detection.
problem Sparse negative binomial regression for count data with non-asymptotic advantages.
method Elastic-net estimator with oracle inequalities derived under Compatibility Factor Condition and Stabil Condition.
result Sign consistency and grouping effect with high probability, and true variable set recovery under certain conditions.
Unified approach for quantum and classical learning from evaluation oracles.
problem Learning from evaluation oracles in quantum and classical settings.
method Inspired by Kearns' SQ and Valiant's weak evaluation oracle, a unified framework is established.
result Characterizes query complexity for learning linear function classes and extends learnability results for quantum circuits.
The paper develops a deep neural network estimator for weakly dependent processes with various loss functions.
problem Learning weakly dependent processes with a broad class of loss functions.
method Sparse-penalized deep neural networks with ψ ψ ψ -weak dependence structure and θ ∞ θ_\infty θ ∞ -coefficients. result Oracle inequalities for the excess risk of the sparse-penalized deep neural networks estimators.
Variable selection for models including interactions between explanatory variables often needs to obey certain hierarchical constraints. The weak or strong structural hierarchy requires that the existence of an interaction term implies at least one or both associated main effects to be present in the model. Lately, thi…
New sampling method for heavy-tailed distributions using Langevin Algorithm.
problem Sampling from heavy-tailed distributions efficiently.
method Transformed Unadjusted Langevin Algorithm on specific transformations.
result Polynomial-order oracle complexities for certain heavy-tailed densities.
Boosting combines weak hypotheses to create accurate predictions under bounded VC dimension.
problem How to combine weak hypotheses to achieve accurate predictions efficiently.
method Designing a novel boosting algorithm with complex aggregation rules for bounded VC dimension classes.
result The new boosting algorithm requires fewer weak hypotheses than classical lower bounds, provided they belong to a bounded VC class.
We develop a new active learning algorithm for the streaming setting satisfying three important properties: 1) It provably works for any classifier representation and classification problem including those with severe noise. 2) It is efficiently implementable with an ERM oracle. 3) It is more aggressive than all previo…
In order to identify important variables that are involved in making optimal treatment decision, Lu et al. (2013) proposed a penalized least squared regression framework for a fixed number of predictors, which is robust against the misspecification of the conditional mean model. Two problems arise: (i) in a world of ex…
New method improves solving combinatorial optimization problems with smoothed policies.
problem Solving combinatorial optimization problems repeatedly with varying instances.
method Smoothed policies with controlled random perturbations to linear oracle, leading to differentiable surrogate risk.
result Generalization bound decomposes excess risk into bias, estimation, and optimization components.
PRISM integrates diverse rewards in MORL, improving sample efficiency and Pareto coverage.
problem Heterogeneous MORL where dense objectives dominate, leading to poor sample efficiency.
method PRISM uses reflectional symmetry and ReSymNet to reconcile temporal-frequency mismatches and accelerate exploration.
result PRISM consistently outperforms sparse-reward baselines and oracles, achieving significant Pareto gains.
We consider an original problem that arises from the issue of security analysis of a power system and that we name optimal discovery with probabilistic expert advice. We address it with an algorithm based on the optimistic paradigm and on the Good-Turing missing mass estimator. We prove two different regret bounds on t…
New bounds on complexity for finding near-stationary points in stochastic convex optimization.
problem Finding near-stationary points in stochastic convex optimization.
method Joint analysis of local stochastic oracle and global oracle models; extensions of recursive regularization technique.
result Logarithmic dependence on smoothness in global oracle model for finding near-stationary points.
New model shows online and statistical learning are computationally equivalent with optimization oracle.
problem Online learning in non-convex games with adversarial settings.
method Strengthening the oracle model to make online and statistical learning computationally equivalent.
result Efficient computation of non-convex game equilibria, including GANs, with optimization oracle.
Paper addresses online alignment of large language models under uncertain preference feedback.
problem Online alignment of large language models with misspecified preference feedback.
method Formulates an oracle-robust objective as a worst-case optimization problem for log-linear policies, and develops projected stochastic composite updates.
result Shows that the robust objective admits an exact closed-form decomposition and achieves O ~ ( ε − 2 ) \widetilde{O}(\varepsilon^{-2}) O ( ε − 2 ) oracle complexity. Mindful active learning improves activity recognition using wearable sensors.
problem Activity recognition using wearable sensors with human cognitive and physical limitations.
method Introduces mindful active learning, a framework that considers human memory and query budget.
result EMMA framework achieves higher accuracy than traditional methods, especially with limited query budgets and weak human memory.
New algorithms sample convex bodies using Markov chains and restricted Gaussian oracles.
problem Sampling uniformly from convex bodies efficiently.
method Markov chain Monte Carlo with proximal sampler and restricted Gaussian oracle.
result Efficient implementation of RGO for uniform sampling on convex bodies.
Approach to detect and adapt to concept drift in unlabeled streaming data.
problem Detect and adapt to concept drift in high-dimensional, noisy, low-context data.
method Density-based clustering for virtual drift and weak supervision for real drift.
result 90% precision in detecting and adapting to concept drift for 4 years after initial deployment.
Quantum oracles help identify counterfactuals better than classical ones.
problem Identifying unknown causal parameters in causal models.
method Using quantum oracles to query and identify all causal parameters and counterfactuals.
result Quantum oracles enable identification of all two-way joint counterfactuals and tighter bounds on higher-order counterfactuals.
New algorithms solve large-scale low-rank and nonsmooth optimization problems efficiently.
problem Solving large-scale composite convex optimization problems with nonsmooth and low-rank terms.
method Stochastic optimization algorithms combining variance reduction and weak proximal oracle.
result First algorithm with nearly optimal sample complexity, single low-rank SVD per iteration, and log 1 / ε \log{1/ε} log 1/ ε thin-SVD computations. The paper tackles sequential mode estimation with oracle queries.
problem Adaptively PAC-learning a probability distribution's mode.
method Two query models: index queries and pair queries. Sequential algorithms for mode estimation.
result Lower bounds on optimal query complexity for both models.
New algorithm solves structured nonconvex-nonconcave min-max problems.
problem Min-max optimization challenges in deep learning.
method Generalized extragradient algorithm for structured nonconvex-nonconcave problems.
result Algorithm converges to stationary points in Euclidean and ℓ p \ell_p ℓ p spaces. Statsformer validates and adapts LLM-derived semantic priors for improved supervised learning.
problem Unreliable semantic priors from LLMs can degrade supervised learning performance.
method Adapts LLM-derived feature scores into a family of learner-specific prior-injection mechanisms, calibrating their influence using out-of-fold validation.
result Improves prediction performance by adaptively downweighting unreliable LLM priors, ensuring a guardrailed statistical learning system.
New algorithm tackles contextual bandits with a regression oracle.
problem Designing practical and theoretically sound algorithms for contextual bandits.
method Leverages a regression oracle to combine realizability-based and agnostic methods.
result Achieves low regret under certain assumptions and comparable/superior performance in empirical evaluations.
New RLHF framework handles general preference oracles without reward functions.
problem Handling general preference oracles without assuming a reward function.
method Developed a minimax game between two LLMs for RLHF under a general preference oracle, focusing on KL-regularized preference.
result Proposed algorithms for efficient offline and online RLHF learning.
FAIRM learns fair and generalizable models by enforcing invariance across different data distributions.
problem Addressing fairness and domain generalization in machine learning models under heterogeneous data.
method FAIRM is a training environment-based oracle that enforces invariance across different data distributions, providing theoretical guarantees and efficient algorithms for linear models.
result FAIRM achieves minimax optimal performance and outperforms existing methods in synthetic and MNIST data evaluations.
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.
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. Simplifies online learning with consistent oracle to fewer mistakes.
problem Online learning with computationally intractable Littlestone dimension computation.
method Novel algorithm making at most O ( 256 d ) O(256^d) O ( 25 6 d ) mistakes, simpler proof. result No algorithm can make less than 3 d 3^d 3 d mistakes. Novel framework learns efficient student models from teacher networks.
problem Model capacity gap between teacher and student networks.
method Neural architecture search and oracle knowledge distillation.
result Searched student models often outperform teacher models.
New algorithms for efficient reinforcement learning with rich observations.
problem Efficient reinforcement learning with rich observations in environments with deterministic dynamics.
method Oracle-efficient algorithms using standard optimization primitives.
result Proved sample efficiency and presented examples of challenges.