A new method improves graph node embeddings by considering both nearby and distant node similarities.
problem Improving graph node embeddings by considering both nearby and distant node similarities.
method Distance-aware Negative Sampling (DNS) which maximizes cohesion at nearby node-pairs and separation at distant node-pairs.
result DNS outperforms baseline methods in downstream node classification tasks on various datasets and GRL algorithms.
Improved sample complexity for Gaussian Mixture Models using Pair Correlation Factor.
problem Understanding the sample complexity of Gaussian Mixture Models.
method Introducing Pair Correlation Factor (PCF) to measure clustering of component means and improving sample complexity bounds.
result The Pair Correlation Factor (PCF) more accurately determines the difficulty of parameter recovery in Gaussian Mixture Models.
A new framework for paired-sample testing in high-dimensional data.
problem Challenges in standard paired-sample testing for high-dimensional data.
method Develops a two-step testing procedure using scoring functions and Wilcoxon signed-rank test.
result Substantial performance gains in testing accuracy compared to traditional methods.
Sampling a fraction of pairs can match full evaluation in machine learning losses.
problem High computational cost of full pairwise loss evaluation.
method Survey sampling techniques targeting informative pairs.
result Performance close to full pairwise evaluation achieved with frugal sampling.
Batchboost stabilizes training by mixing and pairing samples, improving accuracy.
problem Stabilizing training in machine learning, especially avoiding overfitting and underfitting.
method Batchboost pipeline with three stages: pairing, mixing, and feeding. Mixing uses mixup technique.
result Batchboost achieves 0.5-3% better accuracy than mixup on CIFAR-10 & Fashion-MNIST.
New sampling methods improve Shapley values for explaining machine learning predictions.
problem Computational limitations in calculating Shapley values for complex models.
method Asymptotic normality results and paired-sampling approximations (KernelSHAP and PermutationSHAP).
result Paired-sampling PermutationSHAP provides exact results for interactions of maximal order two and has the additive recovery property.
We study the profitability of optimal mean reversion trading strategies in the US equity market. Different from regular pair trading practice, we apply maximum likelihood method to construct the optimal static pairs trading portfolio that best fits the Ornstein-Uhlenbeck process, and rigorously estimate the parameters.…
Nonnegative Matrix Factorization (NMF) has been a popular representation method for pattern classification problem. It tries to decompose a nonnegative matrix of data samples as the product of a nonnegative basic matrix and a nonnegative coefficient matrix, and the coefficient matrix is used as the new representation. …
A new method for conditional sampling using paired Wasserstein Autoencoders.
problem Conditional sampling from complex data distributions.
method Derive a novel loss function for Wasserstein Autoencoders to enable sampling from OT-type couplings.
result Learned cost-optimal transport maps and conditional sampling from an OT-type coupling.
Diffusion models learn simple statistics before complex ones, revealing a sample complexity exponent.
problem Understanding the learning dynamics of diffusion models.
method Empirical observations and theoretical analysis of diffusion models and denoisers.
result Diffusion models learn simple statistics (pair-wise correlations) at linear sample complexity, while higher-order statistics (e.g., fourth cumulant) require cubic sample complexity.
A new method estimates mutual information with fewer paired samples using optimal transport.
problem Estimating mutual information from limited paired samples.
method Semi-supervised Squared-loss Mutual Information (SMI) estimation using optimal transport.
result The method can estimate mutual information with fewer paired samples.
A Triangle Generative Adversarial Network (Δ-GAN) is developed for semi-supervised cross-domain joint distribution matching, where the training data consists of samples from each domain, and supervision of domain correspondence is provided by only a few paired samples. Δ-GAN consists of four neural networks, two ge…
We study the problem of learning similarity functions over very large corpora using neural network embedding models. These models are typically trained using SGD with sampling of random observed and unobserved pairs, with a number of samples that grows quadratically with the corpus size, making it expensive to scale to…
The paper introduces a new pairs trading model using nonlinear and non-Gaussian state-space models.
problem Developing a robust trading strategy for pairs of assets with non-Gaussian and heteroskedastic innovations.
method A nonlinear and non-Gaussian state-space model for the spread between two assets, with mean reversion modeled as a mean-reverting process.
result The new trading strategy yields significantly higher returns and Sharpe ratios compared to existing methods.
The question of aggregating pair-wise comparisons to obtain a global ranking over a collection of objects has been of interest for a very long time: be it ranking of online gamers (e.g. MSR's TrueSkill system) and chess players, aggregating social opinions, or deciding which product to sell based on transactions. In mo…
A new estimator, OddSHAP, simplifies Shapley value computation by focusing on odd components.
problem Efficient computation of Shapley values in machine learning.
method Proved Shapley value depends on odd components, proposed OddSHAP for polynomial regression on odd subspace.
result OddSHAP achieves state-of-the-art estimation accuracy with reduced sampling.
The paper proves impossibilities and positive results for universal machine translation.
problem Learning shared sentence representations across multiple language pairs.
method Formal proofs and analysis of natural generative processes.
result Lower bound on translation error and positive results under natural structure.
Proposes a method to preserve information in heterogeneous domain adaptation.
problem Preserving information in different feature spaces between domains.
method Joint information preservation method integrating paired and structural information.
result Superior performance compared to state-of-the-art HDA algorithms.
Mixup reduces the sample complexity of finding optimal decision boundaries for more separable data.
problem Finding optimal decision boundaries in separable data distributions.
method Mixup technique applied to binary linear classification problems.
result Mixup significantly reduces the sample complexity for more separable data.
MineRL dataset tackles reinforcement learning with over 60M annotated state-action pairs.
problem Sample inefficiency in reinforcement learning methods.
method Large-scale, simulator-paired dataset of human demonstrations in Minecraft.
result Demonstrates the scale, diversity, and difficulty of Minecraft tasks.
Method quantifies relation similarity using entity pair distributions.
problem Measuring similarity between relations in knowledge bases.
method Simple neural network parameterizes conditional probability distributions over entity pairs. Sampling-based approximation for similarity computation.
result Approximation correlates with human judgments and detects redundant relations.
Paper develops tighter risk certificates for contrastive learning models.
problem Statistical theory for contrastive learning is lacking, especially for practical models like SimCLR.
method Develops non-vacuous PAC-Bayesian risk certificates considering practical SimCLR factors.
result Risk certificates for contrastive loss and downstream prediction are much tighter than previous results.
We address the problem of image translation between domains or modalities for which no direct paired data is available (i.e. zero-pair translation). We propose mix and match networks, based on multiple encoders and decoders aligned in such a way that other encoder-decoder pairs can be composed at test time to perform u…
FlexCMH learns effective hashing codes from weakly-paired data.
problem Cross-modal hashing assumes perfect correspondence between samples, which is unrealistic.
method FlexCMH uses clustering-based matching to find potential correspondence and jointly optimizes it with hashing functions.
result FlexCMH achieves significantly better results than state-of-the-art methods.
Obtaining common representations from different modalities is important in that they are interchangeable with each other in a classification problem. For example, we can train a classifier on image features in the common representations and apply it to the testing of the text features in the representations. Existing m…
Though deep reinforcement learning has led to breakthroughs in many difficult domains, these successes have required an ever-increasing number of samples. As state-of-the-art reinforcement learning (RL) systems require an exponentially increasing number of samples, their development is restricted to a continually shrin…
Measures three types of noise in LLM evaluations.
problem Separating signal from noise in LLM experiments.
method Defined and measured three types of noise: prediction, data, and total noise. Proposed the all-pairs paired method for statistical power.
result Total noise level is characteristic and predictable across all model pairs.
In this paper we model the problem of learning preferences of a population as an active learning problem. We propose an algorithm can adaptively choose pairs of items to show to users coming from a heterogeneous population, and use the obtained reward to decide which pair of items to show next. We provide computational…
Develops a framework for multi-objective learning in diffusion models with limited labeled data.
problem Achieving good trade-offs in multi-objective learning with diffusion models requires a generalist model class with larger capacity than individual tasks.
method Proposes a two-stage training procedure: first fitting specialist models from limited paired data, then distilling them into a generalist model.
result Establishes generalization bounds showing the number of paired samples depends only on specialist model complexity.
Paired autoencoders solve inverse problems using latent space projections.
problem Solving inverse problems in scientific computing.
method Paired autoencoder framework that projects data and quantity of interest into a latent space.
result Paired autoencoders generate multiple reconstruction metrics and enable latent-space refinement for accurate data fitting.
New research shows CI in few-shot learning is misleading due to sampling with replacement.
problem Misleading confidence intervals in few-shot learning due to sampling with replacement.
method Comparative analysis of CIs computed with and without replacement.
result Significant underestimation of CI by the predominant method.
Improved KG completion on large datasets using entity-relation pair occurrences.
problem Performance bottleneck in training large-scale KGs due to memory constraints.
method Construct a joint learning model using pairwise occurrence information and increase negative sampling quality.
result Significant improvement in performance, especially with low batch size and negative examples.
Rank aggregation based on pairwise comparisons over a set of items has a wide range of applications. Although considerable research has been devoted to the development of rank aggregation algorithms, one basic question is how to efficiently collect a large amount of high-quality pairwise comparisons for the ranking pur…
Paper presents a method to align unpaired samples across different modalities.
problem Challenges in collecting paired samples for multimodal representation learning.
method Uses propensity score alignment based on Rubin's framework to estimate a common space for unpaired samples.
result Optimal transport matching significantly improves alignment in real-world data.
Unified contrastive learning for likelihood-free inference.
problem Parameter inference in models with intractable likelihood.
method Unified contrastive learning scheme for both density ratio and direct posterior estimation.
result Unified approach clarifies method selection and comparison.
We address the problem of multi-class classification in the case where the number of classes is very large. We propose a double sampling strategy on top of a multi-class to binary reduction strategy, which transforms the original multi-class problem into a binary classification problem over pairs of examples. The aim o…
Algorithm discovers edges between pairs of nodes with limited queries.
problem Discovering good matches between pairs of entities with limited queries.
method Pair-matching problem as a multi-armed bandit with constraints, focusing on Stochastic Block Model.
result Sublinear regret achievable in Stochastic Block Model with two communities, with phase transition related to community detection.
Recent empirical works have successfully used unlabeled data to learn feature representations that are broadly useful in downstream classification tasks. Several of these methods are reminiscent of the well-known word2vec embedding algorithm: leveraging availability of pairs of semantically "similar" data points and "n…
TripleSurv improves survival analysis by ranking samples with time-adaptive adjustments.
problem Modeling censored time-to-event data with high accuracy and robustness.
method Introduces a time-adaptive coordinate loss function to rank samples and calibrate robustness.
result TripleSurv outperforms state-of-the-art methods on various survival datasets.
Study optimal pairs trading with transaction costs using stochastic control.
problem Finding optimal trade times and shares in pairs trading with proportional costs.
method Singular stochastic control approach to solve a nonlinear quasi-variational inequality.
result Developed a discrete time dynamic programming algorithm to compute transaction regions.
Area under the receiver operating characteristics curve (AUC) is an important metric for a wide range of signal processing and machine learning problems, and scalable methods for optimizing AUC have recently been proposed. However, handling very large datasets remains an open challenge for this problem. This paper prop…
New algorithm finds k-centers from noisy distance estimates.
problem Finding k-centers in unknown metric spaces with noisy distance queries.
method Active algorithms using UCB, Thompson Sampling, and Track-and-Stop.
result Approximation ratio of two with high probability.
Optimizes crowdsourced preference-based subjective evaluation with online learning.
problem Large-scale evaluation of generative media using crowdsourcing due to combinatorial explosion.
method Automatic optimization of pair combination selections and evaluation volumes with online learning.
result Optimizes evaluation by reducing pair combinations and allocating optimal evaluation volumes.
Tests assess if predictions are prudent by comparing observations and predictions.
problem Assessing the prudence of predictions in samples of observations and predictions.
method Bootstrap and normal approximation algorithms for testing unweighted and weighted means, accounting for randomness.
result Tests reveal whether predictions are prudent by showing significantly negative mean differences.
The paper proposes new strategies to exploit relationships between meta-tasks for better few-shot learning.
problem Few-shot learning struggles with domain gaps and poorly sampled data.
method Proposes exploiting relationships between meta-tasks to improve robustness and performance.
result Developed new learning objectives (MDA and MKD) to address domain gaps and improve robustness.
GROOVE learns representations for weakly paired multimodal data.
problem Learning representations for high-content perturbation data with weakly paired samples.
method GroupCLIP contrastive loss integrated with an autoencoder framework.
result GROOVE performs on par with or outperforms existing approaches for cross-modal tasks.
Improves off-policy evaluation weights for balanced state-action pair distribution.
problem Imbalance in importance sampling weights for off-policy evaluation of contextual bandits.
method Balanced Off-Policy Evaluation (B-OPE) method that minimizes imbalance to desired counterfactual distribution of state-action pairs.
result Experimental evidence shows B-OPE improves offline policy evaluation in both discrete and continuous action spaces.
Active learning improves ordering of items with contextual attributes.
problem Learning accurate item orderings from pairwise comparisons, especially when exhaustive comparisons are impractical.
method Proposes an active learning strategy that samples items to minimize expected ordering error, accounting for uncertainty in comparisons.
result Superior sample efficiency and generalization compared to non-contextual ranking approaches and active preference learning baselines.