Algorithm improves query recommendations with immediate user feedback.
problem Lack of adaptability to immediate user feedback in query recommendation algorithms.
method Augmented transformer-based causal language models with multi-armed bandit framework.
result Substantial improvement in per-round regret compared to state-of-the-art models.
Efficient exploration improves large language model performance with fewer queries.
problem Improving large language model performance with fewer human feedback queries.
method Sequentially generates queries, fits a reward model to feedback, uses double Thompson sampling with epistemic neural network uncertainty.
result Efficient exploration enables high performance with far fewer queries.
Interactive IL algorithm queries noisy expert for feedback, reducing sample size.
problem Imitation learning with noisy expert feedback requires many samples.
method Selective sampling algorithm with online regression oracle.
result Interactive IL algorithm reduces query complexity and improves performance.
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 L L L in the minimax formulation, multiplicative in L L L in the Bayesian formulation. A new one-point feedback scheme improves ZO algorithms for black-box optimization.
problem Optimizing black-box functions without gradient information.
method Proposes a one-point feedback scheme to estimate gradients using residuals.
result Matches query complexity of two-point schemes for deterministic Lipschitz functions.
Meta-algorithm for efficient reinforcement learning from human preferences.
problem Learning from human preference comparisons in Markov decision processes.
method Randomized exploration and experimental design for batch comparison queries.
result Meta-algorithm achieves both regret and last-iterate guarantees with minimal preference queries.
Paper tackles binary feedbacks in contextual search learning.
problem Learning underlying mean value function in context with binary feedbacks.
method Tri-section search combined with margin-based active learning.
result Algorithm achieves O ( 1 / ε 2 ) O(1/\varepsilon^2) O ( 1/ ε 2 ) queries for ε ε ε -estimation accuracy. A new perceptual adjustment query for metric learning reduces complexity in high-dimensional data.
problem Metric learning in high-dimensional data with limited human feedback.
method Inverted measurement scheme and two-stage estimator for PAQs.
result Sample complexity guarantees for the two-stage estimator of metric learning from PAQs.
Paper proposes efficient RLHF methods for LLMs using active queries.
problem Efficiently aligning LLMs with human preferences using RLHF.
method Formalizes RLHF as a dueling bandit problem, introduces APPO and ADPO algorithms.
result ADPO achieves similar performance to state-of-the-art methods with fewer queries.
Proposes a new query autocompletion method that maximizes retrieval performance.
problem Users often select suboptimal queries due to unknown best retrieval performance.
method Formulates query autocompletion as ranking item rankings, uses counterfactual learning.
result Empirical results show improved query suggestions for better retrieval performance.
New method reduces regret in budgeted learning problems.
problem Decision-making with limited reward queries.
method Confidence-Budget Matching (CBM) principle.
result CBM-based algorithms perform well in adversarial settings.
Projective preferential Bayesian optimization learns user preferences in high dimensions.
problem Finding extrema of a black-box function in high-dimensional spaces.
method Projective preferential queries for feedback in human-interaction.
result Framework finds global minimum of high-dimensional black-box function.
Given a binary prediction problem, which performance metric should the classifier optimize? We address this question by formalizing the problem of Metric Elicitation. The goal of metric elicitation is to discover the performance metric of a practitioner, which reflects her innate rewards (costs) for correct (incorrect)…
New framework selects key features for better query performance prediction.
problem Predict query performance without relevance judgments.
method Step-wise forward and backward feature selection approach.
result Model with selected features performs as well as complex models and better than non-selective models.
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 i l d e O ( s M T ) ilde{\mathcal O}(s\sqrt{M T}) i l d e O ( s M T ) . Algorithm learns diverse rankings for search engines.
problem Designing algorithms for search engines to rank diverse items.
method LDR (Learning Diverse Rankings) algorithm, efficient learning based on users' feedback.
result Algorithm achieves optimal ranking performance with O ( ( N − L ) log ( T ) ) O((N-L)\log(T)) O (( N − L ) log ( T )) regret. Paper tackles dense subgraph discovery with noisy feedback.
problem Discover dense subgraphs in edge-weighted graphs with noisy feedback.
method Proposes polynomial-time and scalable algorithms for dense subgraph discovery.
result Polynomial-time algorithm obtains nearly-optimal solution with high probability.
Bayesian framework for online consensus prediction from expert feedback.
problem Online classification with expert consensus prediction, cost-effective.
method General Bayesian framework for dynamic expert consensus estimation.
result Demonstrated superior performance on large-scale crowdsourced datasets.
No-regret optimization for time-varying functions using uncertainty injection.
problem Optimizing time-varying functions with no-regret in bandit feedback.
method W-SparQ-GP-UCB, incorporating uncertainty injection and additional queries.
result Achieves no-regret with a vanishing number of additional queries per iteration.
The paper tackles efficient change point detection with limited samples.
problem Identifying multiple change points with minimal queries in noisy environments.
method Adaptive algorithm that first detects likely change points and refines their locations.
result The sample complexity is jointly governed by jump magnitudes and change point positions.
New oracle uses uncertainty for active classification with noisy feedback.
problem Improving query complexity in interactive binary classifier learning.
method Proposes a new pairwise comparison oracle that considers uncertainty and an adaptive labeling algorithm.
result Demonstrates improved performance and efficiency compared to existing methods.
Paper develops active learning for clustering unknown pairwise similarities.
problem Learning positive and negative pairwise similarities efficiently.
method Generic active learning framework for correlation clustering.
result Demonstrates effectiveness of query strategies in clustering.
Improves search performance by transferring knowledge from recommender system.
problem Cold start and feedback loop problems in search retrieval.
method Zero-Shot Heterogeneous Transfer Learning framework.
result Significant improvements in relevance and user interactions over production system.
LoCo-RLHF models diverse human feedback with contextual information.
problem Heterogeneous human feedback from diverse contexts and preferences.
method Low-rank contextual preference model, PRS policy.
result LoCo-RLHF achieves tighter sub-optimality gap than existing methods.
Study on collaborative vs. non-collaborative online and bandit convex optimization.
problem Minimizing average regret in distributed online and bandit convex optimization.
method Analyzes the impact of collaboration in adaptive and zeroth-order feedback settings.
result Collaboration is beneficial in high-dimensional federated online optimization with limited feedback.
New algorithm guarantees performance on noisy data.
problem Learning with noisy data and heavy-tailed distributions.
method Anytime online-to-batch conversion for smooth objectives.
result Stochastic gradient-based algorithm with sub-Gaussian error bounds.
New approach mitigates feedback divergence in imitation learning.
problem Divergence between held-out error and learner performance in imitation learning.
method Identifies covariate shift as the root cause and proposes a simulator-based solution.
result Naive behavioral cloning performs well in real-world decision making problems.
Search-oriented conversational systems rely on information needs expressed in natural language (NL). We focus here on the understanding of NL expressions for building keyword-based queries. We propose a reinforcement-learning-driven translation model framework able to 1) learn the translation from NL expressions to que…
Proposes a new theoretical framework for PbRL that requires less human feedback.
problem Lack of theoretical work capturing practical PbRL frameworks.
method Introduces a reward-agnostic PbRL framework that acquires exploratory trajectories before human feedback.
result Demonstrates improved sample complexity for learning optimal policies in linear and low-rank MDPs.
Study reduces human labeling in LLM-based classification systems.
problem Minimizing human intervention in training LLM-based classification systems.
method Active learning framework with Conservative Hull-based Classifier (CHC), Center-based Classifier (CC), and Generalized Hull-based Classifier (GHC).
result CHC achieves O ( log d T ) \mathcal{O}(\log^d T) O ( log d T ) regret and is minimax optimal for d = 1 d=1 d = 1 . GHC bridges the gap between different regimes. Active learning optimizes correlation clustering by querying the most informative pairwise comparisons.
problem Efficiently clustering data with limited pairwise similarity information.
method Developed principled active learning approach using information-theoretic acquisition functions.
result Significantly outperforms existing baselines in clustering accuracy and query efficiency.
New methods improve black-box adversarial attacks with fewer queries.
problem Efficiently craft adversarial examples without access to gradients.
method Prior-guided random gradient-free algorithms based on biased sampling and gradient averaging.
result Both methods require fewer queries and achieve higher success rates.
Language models learn automotive complaints, improving defect detection.
problem Detecting technical quality issues in customer feedback.
method Continual pre-training on ODI Complaints data set.
result Models achieve high precision in identifying technical terms.
An interactive image retrieval system learns which images in the database belong to a user's query concept, by analyzing the example images and feedback provided by the user. The challenge is to retrieve the relevant images with minimal user interaction. In this work, we propose to solve this problem by posing it as a …
MAXMINLCB optimizes unknown target functions with preference feedback using a Stackelberg game approach.
problem Optimizing unknown target functions with pairwise comparisons and human feedback.
method MAXMINLCB, a zero-sum Stackelberg game, balances exploration and exploitation.
result MAXMINLCB consistently outperforms existing algorithms with a rate-optimal regret guarantee.
Safe RL with binary feedback using SABRE algorithm.
problem Safe reinforcement learning with binary safety feedback.
method SABRE algorithm, combining active learning and reinforcement learning.
result Provable safe policy with high probability, no unsafe actions during training.
We consider the black-box adversarial setting, where the adversary has to generate adversarial perturbations without access to the target models to compute gradients. Previous methods tried to approximate the gradient either by using a transfer gradient of a surrogate white-box model, or based on the query feedback. Ho…
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 method tackles online DR-submodular maximization with improved regret guarantees.
problem Online maximization of non-monotone DR-submodular functions over down-closed convex sets.
method 1/e-linearization through exponential reparametrization, surrogate potential, and reduction to online linear optimization.
result Achieves O ( T 1 / 2 ) O(T^{1/2}) O ( T 1/2 ) static regret with single gradient query per round, improving state of the art. Dual active learning improves RLHF by selecting optimal conversations and teachers.
problem Efficiently aligning LLMs with human preferences using RLHF from feedback.
method Offline RL for conversation and teacher selection, dual active reward learning, pessimistic RL.
result The proposed algorithm achieves minimal generalized variance and outperforms state-of-the-arts.
We study pool-based active learning with abstention feedbacks where a labeler can abstain from labeling a queried example with some unknown abstention rate. This is an important problem with many useful applications. We take a Bayesian approach to the problem and develop two new greedy algorithms that learn both the cl…
We study pool-based active learning with abstention feedbacks, where a labeler can abstain from labeling a queried example with some unknown abstention rate. This is an important problem with many useful applications. We take a Bayesian approach to the problem and develop two new greedy algorithms that learn both the c…
A method identifies abrupt changes in functions with fixed confidence under noisy feedback.
problem Identifying abrupt changes in piecewise constant functions quickly and with certainty.
method Fixed-confidence piecewise constant bandit problem, focusing sampling efforts near change points.
result Asymptotically optimal method proven computationally efficient and effective in experiments.
We develop a learning principle and an efficient algorithm for batch learning from logged bandit feedback. This learning setting is ubiquitous in online systems (e.g., ad placement, web search, recommendation), where an algorithm makes a prediction (e.g., ad ranking) for a given input (e.g., query) and observes bandit …
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.
Proposes an online model for LLM cascading with adaptive API selection.
problem Adaptive querying and selection of LLM APIs in a context-dependent environment.
method Develops a learning approach combining GMM estimation and UCB-style bounds.
result Achieves cumulative regret of O ~ ( T ) \widetilde O(\sqrt T) O ( T ) over T T T periods. CEGA addresses GNN security by enabling cost-effective model acquisition.
problem Vulnerability of Graph Neural Networks (GNNs) to model extraction attacks (MEAs).
method Proposes an adaptive node querying strategy to refine node selection over multiple learning cycles.
result Demonstrates superior performance in accuracy, fidelity, and F1 score under strict query-size constraints.
New method calibrates probabilistic linear solver for online coverage guarantees.
problem Uncertainty in probabilistic linear solver solutions without coverage guarantees.
method Online conformal prediction-PLS (OCP-PLS) method to calibrate uncertainty thresholds.
result Validates online calibration of uncertainty thresholds via online conformal prediction.