The scalability of the labeling process and the attainable quality of labels have become limiting factors for many applications of machine learning. The programmatic creation of labeled datasets via the synthesis of noisy heuristics provides a promising avenue to address this problem. We propose to improve modeling of …
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.
168,695 papers · 148 categories
Trend · papers per month
48 results for “pairwise feedback”
SetRank tackles collaborative ranking from implicit feedback using setwise Bayesian approach.
problem Challenges in pairwise and listwise approaches for implicit feedback.
method SetRank is a novel setwise Bayesian approach that accommodates implicit feedback characteristics.
result SetRank outperforms state-of-the-art baselines on real-world datasets.
A Markov Chain approach for aligning generative models from pairwise human preferences.
problem Aligning generative models from pairwise human preferences.
method Markov Chain from Human Feedback (MCHF)
result MCHF converges geometrically fast to the stationary distribution.
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)…
The paper proposes a new method for learning reward models from ordinal feedback, improving upon binary feedback.
problem Learning reward models from human preferences using binary feedback discards useful samples and loses fine-grained information.
method The paper introduces a framework for learning reward models under ordinal feedback, generalizing the Bradley-Terry model.
result Ordinal feedback reduces the Rademacher complexity compared to binary feedback, leading to better reward learning.
The paper analyzes RLHF with human feedback and provides convergence results for MLE and pessimistic MLE.
problem Improving RLHF with human feedback from pairwise or -wise comparisons.
method Theoretical framework for RLHF with convergence analysis of MLE and pessimistic MLE.
result MLE fails but pessimistic MLE provides improved policies under certain coverage assumptions.
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.
We present a study on reinforcement learning (RL) from human bandit feedback for sequence-to-sequence learning, exemplified by the task of bandit neural machine translation (NMT). We investigate the reliability of human bandit feedback, and analyze the influence of reliability on the learnability of a reward estimator,…
Paper characterizes minimax regret rates for online ranking with top-k feedback.
problem Analyzing online ranking with partial feedback.
method Developed techniques from partial monitoring to characterize minimax regret rates.
result Full characterization of minimax regret rates for Precision@n.
We consider the problem of probably approximately correct (PAC) ranking items by adaptively eliciting subset-wise preference feedback. At each round, the learner chooses a subset of items and observes stochastic feedback indicating preference information of the winner (most preferred) item of the chosen subset …
A Finite Time Analysis of Thompson Sampling for Bayesian Optimization with Preferential Feedbackstat.ML
Proposes a TS approach for Bayesian optimization with preferential feedback.
problem Optimizing with preference feedback in complex applications.
method Uses Thompson Sampling with a dueling kernel and anchor invariance.
result Performance matches standard TS for scalar feedback in finite time.
Stochastic structured prediction under bandit feedback follows a learning protocol where on each of a sequence of iterations, the learner receives an input, predicts an output structure, and receives partial feedback in form of a task loss evaluation of the predicted structure. We present applications of this learning …
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.
PDO optimizes LLM prompts without labels, improving performance.
problem Optimizing prompts for LLMs without access to labeled data.
method Pairwise preference feedback, dueling bandits, Thompson Sampling, mutation.
result PDO identifies stronger prompts than label-free methods.
Local PBO methods improve preferential BO in high-dimensional problems.
problem Efficiently optimizing preferential BO in high-dimensional settings.
method Adapting high-dimensional BO techniques to preferential feedback.
result Local PBO methods reduce cumulative regret compared to global baselines.
RCPO uses ranked choice modeling for better LLM alignment.
problem Pairwise preference optimization limits LLM alignment.
method Unified framework combining preference optimization and ranked choice modeling.
result RCPO outperforms competitive baselines in LLM alignment.
RL-LOW algorithm achieves exponential simple regret in offline RLHF with pairwise comparisons.
problem Offline reinforcement learning from human feedback with pairwise comparisons.
method Proposes RL-LOW algorithm to minimize simple regret with exponential convergence.
result Achieves an exponential form of simple regret of \(\exp ( - Ω(n/H) )\).
Robot motions in the presence of humans should not only be feasible and safe, but also conform to human preferences. This, however, requires user feedback on the robot's behavior. In this work, we propose a novel approach to leverage the user's brain signals as a feedback modality in order to decode the judgment of rob…
Study on deep neural networks for reward modeling with pairwise comparison data.
problem Reward modeling with deep neural networks in non-parametric settings.
method Established a non-asymptotic regret bound for deep reward estimators, introduced a margin-type condition.
result Improved regret bound for deep reward estimators, highlighting the importance of clear human beliefs.
Proposes a method for ranking items across multiple aspects based on user feedback.
problem No principled solution exists for generating multiple item rankings over different aspects.
method Developed a directional multi-aspect ranking criterion using probabilistic multivariate tensor factorization.
result Demonstrated effectiveness of the proposed method through comprehensive experiments on real datasets.
Unified LP framework for offline reward learning from human demonstrations and feedback.
problem Reward learning from human demonstrations and feedback with robustness and sample efficiency.
method A novel linear programming framework for offline reward learning.
result Unified LP framework achieves better performance compared to MLE.
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.
Recommender systems play a crucial role in mitigating the problem of information overload by suggesting users' personalized items or services. The vast majority of traditional recommender systems consider the recommendation procedure as a static process and make recommendations following a fixed strategy. In this paper…
Preference-based Reinforcement Learning beyond Pairwise Comparisons: Benefits of Multiple Optionscs.LG
Improved sample efficiency in preference-based RL with multiple comparisons.
problem Sample inefficiency in preference-based reinforcement learning with pairwise comparisons.
method Proposes M-AUPO, an algorithm that selects multiple actions by maximizing average uncertainty within subsets.
result Achieves a suboptimality gap of $O\left( \frac{d}{T} \sqrt{ \sum_{t=1}^T \frac{1}{|S_t|}}
ight)$, improving performance with larger subsets.
RLHF performs well despite violating social choice theory axioms.
problem RLHF's empirical success contradicts social choice theory axioms.
method Showed RLHF satisfies pairwise majority and Condorcet consistency under mild assumptions, and introduced new alignment criteria.
result RLHF satisfies pairwise majority and Condorcet consistency under mild assumptions, explaining its practical success.
Unified framework for aligning LLMs from human feedback.
problem Lack of strong theoretical justification for RLHF and inability to compare methods.
method Reframed alignment as distribution learning from pairwise preferences, proposing three principled objectives.
result Proposed objectives achieve strong non-asymptotic convergence to target LM.
In this paper, we propose a novel ranking framework for collaborative filtering with the overall aim of learning user preferences over items by minimizing a pairwise ranking loss. We show the minimization problem involves dependent random variables and provide a theoretical analysis by proving the consistency of the em…
DOPL learns from preference feedback to solve RMAB problems.
problem Learning optimal decisions in RMAB with limited reward information.
method Direct online preference learning (DOPL) for Pref-RMAB.
result DOPL achieves sublinear regret for RMAB with preference feedback.
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.
New framework PBBO optimizes latent functions with preferential feedback.
problem Optimizing latent functions with parallel preferential feedback.
method Gaussian process model with a likelihood for parallel comparisons.
result Framework PBBO generalizes and expands Bayesian optimization.
Algorithm aggregates rewards from multiple players to learn related tasks in online bandit learning.
problem Learning related but slightly different tasks in an online setting with heterogeneous feedback.
method RobustAgg algorithm that aggregates rewards from different players.
result Achieves instance-dependent regret guarantees and nearly matching lower bounds.
In this paper, we propose a listwise approach for constructing user-specific rankings in recommendation systems in a collaborative fashion. We contrast the listwise approach to previous pointwise and pairwise approaches, which are based on treating either each rating or each pairwise comparison as an independent instan…
RLHF uses human feedback to train AI models, posing statistical challenges.
problem Aligning AI models with human preferences using noisy, subjective feedback.
method Supervised fine-tuning, reward modeling, policy optimization, statistical ideas.
result Statistical methods for reward function learning and policy optimization.
JoVA combines two VAEs to learn user and item representations for better recommendation.
problem Collaborative filtering with implicit feedback.
method Joint Variational Autoencoders (JoVA) with a hinge-based pairwise loss function (JoVA-Hinge).
result JoVA-Hinge outperforms state-of-the-art methods in top-k recommendation.
ATPboost is a system for solving sets of large-theory problems by interleaving ATP runs with state-of-the-art machine learning of premise selection from the proofs. Unlike many previous approaches that use multi-label setting, the learning is implemented as binary classification that estimates the pairwise-relevance of…
Algorithm identifies best item from subsets with random utility model feedback.
problem PAC learning the best item from subsets with random utility model feedback.
method Pairwise relative counts and hierarchical elimination for learning algorithm.
result Near-optimal PAC sample complexity guarantee for identifying ε-optimal item.
In supervised learning, we typically leverage a fully labeled dataset to design methods for function estimation or prediction. In many practical situations, we are able to obtain alternative feedback, possibly at a low cost. A broad goal is to understand the usefulness of, and to design algorithms to exploit, this alte…
A new approach to fine-tuning LLMs with human feedback.
problem Inability of current reward models to fully represent human preferences.
method Introducing NLHF, a new pipeline for LLM fine-tuning using pairwise human feedback.
result NLHF produces a sequence of policies converging to the regularized Nash equilibrium.
This thesis tackles learning reward functions from human comparative feedback.
problem Designing reward functions for complex tasks is challenging and humans often provide suboptimal demonstrations.
method Proposes learning reward functions from comparative feedback (pairwise comparisons, best-of-many choices, rankings, scaled comparisons) and active learning techniques.
result Demonstrates the effectiveness of learning reward functions from comparative feedback in various domains.
We introduce the probably approximately correct (PAC) \emph{Battling-Bandit} problem with the Plackett-Luce (PL) subset choice model--an online learning framework where at each trial the learner chooses a subset of arms from a fixed set of arms, and subsequently observes a stochastic feedback indicating prefere…
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.
We address the problem of maximizing an unknown submodular function that can only be accessed via noisy evaluations. Our work is motivated by the task of summarizing content, e.g., image collections, by leveraging users' feedback in form of clicks or ratings. For summarization tasks with the goal of maximizing coverage…
Advances in collaborative filtering and ranking methods.
problem Improving recommendation systems efficiency and accuracy.
method Graph information encoding, pairwise and listwise approaches, regularization techniques, personalization.
result New methods significantly improve recommendation system performance.
The paper explores game-theoretic alignment of LLMs with human preferences, finding limitations and conditions.
problem Aligning LLMs with human preferences using game theory.
method Systematic study of payoff choices in a two-player zero-sum game for desirable alignment properties.
result Impossibility of preference matching in game-theoretic LLM alignment under standard assumptions.
Adaptive reward models capture individual preferences from human feedback.
problem Learning a reward model that can be specialised to a user.
method Empirical risk minimisation and PAC bound analysis.
result Adaptive reward models benefit from the heterogeneity of user preferences.
This thesis formalizes metric selection for machine learning applications.
problem Selecting the right performance metric for machine learning models.
method Metric Elicitation framework using pairwise preference feedback.
result Novel strategies for eliciting various classification metrics robust to noise.
New model improves recommendation systems by analyzing user-item interactions.
problem Improving recommendation systems for better user-item interactions.
method Sliced Anti-symmetric Decomposition (SAD) model using tensor decomposition.
result SAD produces the most consistent personalized preferences compared to SOTA models.
Clustering with Fast, Automated and Reproducible assessment applied to longitudinal neural trackingstat.ML
C-FAR automates clustering assessment for neural tracking.
problem Manual assessment of clusters by humans is slow and impractical for large datasets.
method C-FAR uses automated feedback queries to select optimal clustering from multiple algorithms.
result C-FAR produces near-perfect clustering on simulated neural data.