Paper proposes an unbiased classifier from triplet comparison data.
problem Learning a classifier from triplet comparison data.
method Empirical risk minimization framework with an unbiased estimator.
result The proposed method achieves better performance than baseline methods.
New method improves prediction accuracy in comparison data.
problem Efficiently predicting outcomes in limited comparison data.
method Empirical Bayes shrinkage methods for pairwise uncertainty estimation.
result Empirical Bayes shrinkage outperforms standard methods in comparison data.
SC improves robustness in model comparison for misspecified models.
problem Model misspecification challenges in amortized Bayesian inference.
method Parameter posterior-based methods augmented with SC training.
result SC improves robustness under model misspecification.
New model reduces bias in crowdsourced pairwise comparisons.
problem Crowdsourced pairwise comparisons are biased due to perceptual factors.
method factorBT model accounts for irrelevant factors affecting worker answers.
result factorBT produces more accurate rankings than previous models.
The paper examines how optimizer comparisons in deep learning are influenced by hyperparameter tuning.
problem The sensitivity of optimizer comparisons to hyperparameter tuning protocols.
method Empirical comparisons of optimizers with and without varying hyperparameter search spaces.
result Inclusion relationships between optimizers matter in practice and can contradict recent empirical comparisons.
Paper tackles clustering with ordinal comparisons, achieving near-optimal results.
problem Clustering with ordinal comparisons when similarity measures are not available.
method Two-step procedure: estimate similarity matrix from comparisons, then apply SDP clustering.
result Near-optimal recovery of planted clustering using near-optimal number of comparisons.
Efron et al. (2001) proposed empirical Bayes formulation of the frequentist Benjamini and Hochbergs False Discovery Rate method (Benjamini and Hochberg,1995). This article attempts to unify the `two cultures' using concepts of comparison density and distribution function. We have also shown how almost all of the existi…
We performed an empirical comparison of ICA and PCA algorithms by applying them on two simulated noisy time series with varying distribution parameters and level of noise. In general, ICA shows better results than PCA because it takes into account higher moments of data distribution. On the other hand, PCA remains quit…
Develops comparison-based hierarchical clustering algorithms without object representations.
problem Hierarchical clustering without object representations or pairwise similarities.
method Comparison-based hierarchical clustering algorithms (single, complete, and average linkage variants).
result Statistical guarantees and empirical performance on various datasets.
Proposes a revenue function to evaluate dendrograms from comparisons.
problem Evaluate dendrograms from comparisons without ground-truth.
method Introduces a new revenue function related to Dasgupta's cost.
result Revenue function allows meaningful evaluation of dendrograms.
DECS tool assesses swap rates of DEXes and Fusion outperforms competitors.
problem Lack of unbiased swap rate comparisons in decentralized finance.
method Swap transaction monitoring and simulation techniques.
result 1inch Classic and Fusion consistently outperform competitors in swap rates.
TripletBoost learns classifiers from noisy triplet comparisons.
problem Learning from comparison-based data.
method Aggregate weak classifiers from weakly learned triplets, then boost.
result Theoretical guarantees and empirical competitiveness.
A new metric uses nonparametric comparison for fitting parametric distributions.
problem Measuring goodness-of-fit for nonlinear models using maximum likelihood estimation.
method Survival Jensen-Shannon divergence ( S J S SJS S J S ) and its empirical counterpart ( E S J S {\cal E}SJS E S J S ) for nonparametric comparison. result The E S J S {\cal E}SJS E S J S can be used as a measure of goodness-of-fit in maximum likelihood estimation. Study metric learning from limited preference comparisons, showing how low-dimensional structure can still reveal metric information.
problem Learning metric from limited pairwise preference comparisons.
method Ideal point model, divide-and-conquer approach for low-dimensional structure.
result Metric can be jointly identified even with limited comparisons when items exhibit low-dimensional structure.
We address the problem of learning a ranking by using adaptively chosen pairwise comparisons. Our goal is to recover the ranking accurately but to sample the comparisons sparingly. If all comparison outcomes are consistent with the ranking, the optimal solution is to use an efficient sorting algorithm, such as Quicksor…
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.
We propose the point process model as the Poissonian-like stochastic sequence with slowly diffusing mean rate and adjust the parameters of the model to the empirical data of trading activity for 26 stocks traded on NYSE. The proposed scaled stochastic differential equation provides the universal description of the trad…
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.
Develops a statistical framework to measure uncertainty in model rankings based on human preferences.
problem Uncertainty in model rankings based on human preferences due to mismatch between human and model preferences.
method Statistical framework using pairwise comparisons by humans and models to provide rank-sets for each model.
result Rank-sets constructed using only pairwise comparisons by strong models often do not cover the true ranking of human preferences.
SyncRank recovers global ranking from noisy comparisons with theoretical guarantees.
problem Recovering a global ranking from noisy pairwise comparisons.
method Complex-valued data model and SDP relaxation for exact ranking recovery.
result SyncRank achieves exact ranking recovery with high probability above a critical noise threshold of O(sqrt(n / log n)).
This work analyzes Fréchet regression using comparison geometry, providing theoretical and practical insights.
problem Analyzing data on complex structures like manifolds and graphs.
method Theoretical analysis through comparison geometry, focusing on existence, uniqueness, and stability of the Fréchet mean.
result Key results on the existence, uniqueness, and stability of the Fréchet mean, along with statistical guarantees for nonparametric regression.
The paper introduces uncertainty estimates for embedding objects based on noisy triplet comparisons.
problem Learning from ordinal data without a distance metric.
method Bootstrap and Bayesian approaches to estimate uncertainty for embedding algorithms.
result Empirical uncertainty estimates are well-calibrated and useful for selecting parameters or quantifying uncertainty.
Herd behavior is an important economic phenomenon, especially in the context of the recent financial crises. In this paper, herd behavior in global stock markets is investigated with a focus on intercontinental comparison. Since most existing herd behavior indices do not provide a comparative method, we propose a new h…
A new method learns from pairwise comparisons to predict sensitive data without making strong assumptions.
problem Predicting sensitive data like annual income from unlabeled data with unknown target correspondence.
method Utilizes pairwise comparison data to learn a regression model without strong assumptions.
result The learned model converges to optimal with optimal parametric rate for uniformly distributed targets.
CPS methods improve sample efficiency in robotics.
problem Improving sample efficiency in reinforcement learning for robotics.
method Empirical evaluation of C-CMA-ES with active covariance matrix adaptation and comparison-based surrogate model.
result Improvements in sample efficiency with C-CMA-ES extensions.
Reviews techniques for model evaluation, selection, and algorithm comparison in machine learning.
problem Ensuring correct use of model evaluation, selection, and algorithm selection techniques in machine learning.
method Reviews and discusses various techniques for model evaluation, selection, and algorithm comparison, including holdout method, bootstrap, cross-validation, and statistical tests.
result Best practices and recommendations for model evaluation, selection, and algorithm comparison are provided.
Modeling preference rankings with salient features to explain irrational choices.
problem Estimating rankings from noisy pairwise comparisons with irrational choices.
method Salient feature preference model with maximum likelihood estimation.
result Strong performance of maximum likelihood estimation on synthetic and real data.
ERM with square loss achieves sublinear error for learnable function classes with smoothed data.
problem Statistical and computational hardness in sequential decision-making.
method Empirical Risk Minimization (ERM) with square loss, focusing on unknown base measure and smooth data.
result ERM achieves error scaling as i l d e O ( c o m p ( F ) ⋅ T ) ilde O( \sqrt{\mathrm{comp}(\mathcal F)\cdot T} ) i l d e O ( comp ( F ) ⋅ T ) for learnable function classes. The main object of Bayesian statistical inference is the determination of posterior distributions. Sometimes these laws are given for quantities devoid of empirical value. This serious drawback vanishes when one confines oneself to considering a finite horizon framework. However, assuming infinite exchangeability gives…
Generative Adversarial Networks create realistic financial correlation matrices.
problem Creating realistic financial correlation matrices for practical applications.
method Generative Adversarial Networks (GANs) to model correlation matrices.
result GANs can recover known stylized facts about empirical correlation matrices.
This paper compares FAISS and FENSHSES for nearest neighbor search in Hamming space.
problem Comparing nearest neighbor search systems in Hamming space.
method Comprehensive evaluations of indexing speed, search latency, and RAM consumption.
result Better understanding of trade-offs between main memory and secondary memory systems.
We study the K K K -armed dueling bandit problem, a variation of the standard stochastic bandit problem where the feedback is limited to relative comparisons of a pair of arms. We introduce a tight asymptotic regret lower bound that is based on the information divergence. An algorithm that is inspired by the Deterministic…
We study a new ensemble of random correlation matrices related to multivariate Student (or more generally elliptic) random variables. We establish the exact density of states of empirical correlation matrices that generalizes the Marcenko-Pastur result. The comparison between the theoretical density of states in the St…
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.
New algorithm learns human preferences from few comparisons efficiently.
problem Learning human preferences from limited comparison feedback.
method Formulated as D-optimal design for Plackett-Luce model, solved using randomized Frank-Wolfe algorithm.
result Proposed algorithm efficiently solves D-optimal design problem for Plackett-Luce objective.
The paper designs tests for comparing ranked preference data and finds significant differences.
problem Comparing pairwise comparison and ranking data in various applications.
method Developed two-sample tests for pairwise comparison and ranking data, proving upper and lower bounds.
result Upper and lower bounds show tightness of the proposed tests, and significant differences in preferences were found.
Develops a method to infer partial rankings from sparse comparisons.
problem Challenges in ranking items with limited and noisy comparisons.
method Nonparametric Bayesian approach for learning partial rankings.
result Finds partial rankings that distinguish meaningful differences only when data supports it.
Paper introduces an efficient comparison operator for robust multi-objective optimization with uncertain objectives.
problem Optimizing with uncertain objectives in multi-objective problems.
method Empirical approach to compare solutions with arbitrary distributions of uncertain objectives.
result Higher optimization quality achieved at lower overheads compared to existing techniques.
We study the dependence structure of market states by estimating empirical pairwise copulas of daily stock returns. We consider both original returns, which exhibit time-varying trends and volatilities, as well as locally normalized ones, where the non-stationarity has been removed. The empirical pairwise copula for ea…
Bispectral OT improves dataset comparison by preserving intrinsic coherence.
problem Ignoring intrinsic coherence in dataset comparisons using pairwise geometric distances.
method Introduces Bispectral Optimal Transport, a symmetry-aware extension of discrete OT.
result Transport plans computed with Bispectral OT achieve greater class preservation accuracy.
Bayesian method infers contextual bandit policies robustly.
problem Inference of contextual bandit policies in small sample sizes.
method Empirical likelihood for Bayesian inference.
result Accurate uncertainty measurements and policy comparison.
Extends covariance estimation with multiple targets for better performance.
problem Improving covariance estimation for multiple targets.
method Combines multiple constant matrices with sample covariance matrix, derives estimators and proves convergence.
result The multi-target linear shrinkage estimator outperforms other estimators in various situations.
This paper extends Median-of-Means to new learning problems involving pairwise comparisons.
problem Learning from pairwise comparisons in machine learning.
method Segmenting data into blocks, comparing pairs of decision rules, and declaring the winner based on majority performance.
result The Median-of-Means approach maintains robustness and performance under various sampling schemes.
We review statistical properties of models generated by the application of a (positive and negative order) fractional derivative operator to a standard random walk and show that the resulting stochastic walks display slowly-decaying autocorrelation functions. The relation between these correlated walks and the well-kno…
Paper investigates monotonicity issues in AI preference learning.
problem AI models may violate monotonicity when learning preferences.
method Investigates root causes of non-monotonicity in comparison-based preference learning.
result Proves local pairwise monotonicity under mild assumptions.
Box Thirding identifies the best arm efficiently under limited samples.
problem Efficiently identifying the best arm with limited sampling.
method Iterative ternary comparison of arms, discarding the weakest and exploring the best.
result Achieves comparable performance to Successive Halving with less predefined parameters.
Improves Active Learning fairness and comparability across domains.
problem Inconclusive Active Learning research due to domain-specific results.
method Develops a fair comparison framework and oracle algorithm.
result Empirical results rank 6 algorithms across 3 domains.
COPT optimizes graph distances via simultaneous optimal transport.
problem Learning graph representations unsupervisedly.
method Simultaneous optimization of dual transport plans between vertices and graph signals.
result COPT preserves spectral information and outperforms state-of-the-art methods.