GAAVI offers anytime-valid tests for CMF global null and contrasts.
problem Inference on the conditional mean function for high confidence decisions.
method Asymptotic anytime-valid tests for CMF global null and contrasts.
result Achieves asymptotic type-I error guarantees, power one, and optimal sample complexity.
New method tests causal association using noise contrastive backdoor adjustment.
problem Testing causal association in complex settings with many confounders.
method Backdoor-HSIC (bd-HSIC) using HSIC for independence testing.
result Calibrated and powerful for binary and continuous treatments with many confounders.
The paper develops a method to learn cost-optimal sequential testing policies from retrospective data.
problem Learning cost-optimal sequential decision policies from retrospective data with missing test results.
method Doubly robust Q-learning framework with path-specific inverse probability weights.
result The method reduces testing cost without compromising predictive accuracy.
Two tests identify heterogeneous components in distributed learning.
problem Identifying parameter heterogeneity in distributed learning with minimal data transmission.
method Two tests: Wald and Extreme Contrast (ECT).
result ECT avoids bias accumulation and is robust to varying levels of sparsity.
AutoSciDACT detects scientific anomalies in noisy data.
problem Detecting anomalies in large, noisy scientific datasets.
method Contrastive pre-training for low-dimensional data representations, two-sample test using NPLM.
result Strong sensitivity to small anomalies across various scientific domains.
A new contrastive learning method extracts asset embeddings from financial time series.
problem Extracting meaningful latent features from noisy financial data.
method Contrastive learning framework using hypothesis testing for positive and negative samples.
result Effective asset embeddings significantly outperform existing methods on financial tasks.
Improves contrastive learning invariance with novel training objectives and feature averaging.
problem Contrastive learning's implicit invariance is insufficient for robust performance.
method Introduces a novel training objective and feature averaging approach to enforce invariance.
result Improved performance and robustness to transformations on downstream tasks.
Deep Learning is a promising approach to either automate or simplify several tasks in the healthcare domain. In this work, we introduce SegAN-CAT, an approach to brain tumor segmentation in Magnetic Resonance Images (MRI), based on Adversarial Networks. In particular, we extend SegAN, successfully applied to the same t…
BrainSurfCNN predicts task contrasts from resting-state fingerprints, improving accuracy over baseline.
problem Predicting task-evoked activity from resting-state functional connectivity.
method Surface-based convolutional neural network (BrainSurfCNN) with reconstructive-contrastive loss.
result Significantly improved accuracy in predicting task contrasts over baseline.
New test assesses probabilistic model calibration without expensive approximations.
problem Assessing calibration of probabilistic models with scores.
method Kernel Calibration Conditional Stein Discrepancy (KCCSD) test using new score-based kernels.
result Control over type-I error with improved scalability and efficiency.
Replicated and validated Rank-N-Contrast for robust regression.
problem Deep regression models struggle with continuous sample orders.
method Contrastive learning of continuous representations by ranking samples.
result Improved performance and robustness of RNC framework.
With the advent of GDPR, the domain of explainable AI and model interpretability has gained added impetus. Methods to extract and communicate visibility into decision-making models have become legal requirement. Two specific types of explanations, contrastive and counterfactual have been identified as suitable for huma…
Semi-supervised learning improves with partial label information.
problem Improving model performance with limited labeled data.
method Contrastive learning with partial label information to encourage same labels.
result Partial label information reduces test error by up to 5.5 times.
Develops a new self-supervised learning method combining contrastive and non-contrastive approaches.
problem Leveraging unlabeled data for representation learning, especially with high variance and low batch sizes.
method Converts a contrastive method (Spectral Contrastive Loss) into a non-contrastive form (MINC loss) to reduce variance and mutual information.
result MINC loss consistently improves upon the Spectral Contrastive loss baseline in learning image representations.
A family of maximum mean discrepancy (MMD) kernel two-sample tests is introduced. Members of the test family are called Block-tests or B-tests, since the test statistic is an average over MMDs computed on subsets of the samples. The choice of block size allows control over the tradeoff between test power and computatio…
Deep learning predicts response to HER2-targeted breast cancer therapy.
problem Predicting response to HER2-targeted neoadjuvant chemotherapy.
method Developed and validated a deep learning approach using pre-treatment dynamic breast MRI.
result Deep learning model achieved strong performance in predicting pathological complete response.
This work identifies redundant tests in conditional-independence-based discovery that can improve graphical model accuracy.
problem Reliability and sensitivity of conditional-independence-based discovery algorithms.
method Analysis of redundant tests and their impact on error detection and correction.
result Redundant tests can improve graphical model accuracy but not all are beneficial.
Testing whether a probability distribution is compatible with a given Bayesian network is a fundamental task in the field of causal inference, where Bayesian networks model causal relations. Here we consider the class of causal structures where all correlations between observed quantities are solely due to the influenc…
Paper proposes a new regularization method to prevent model degradation under distribution shifts.
problem Model performance degrades under distribution shifts.
method Supervised contrastive learning with heterogeneous similarity.
result The proposed method outperforms existing regularization methods on benchmark datasets.
New method detects watermarks in LLM-generated text with human edits.
problem Dilution of watermark signals by human edits on LLM-generated text.
method Truncated goodness-of-fit test (Tr-GoF) for robust detection.
result Tr-GoF achieves optimality in robust detection of Gumbel-max watermark.
The study analyzes group testing algorithms for identifying defective items with high confidence.
problem Identifying defective items from a population using group testing with high confidence.
method Formulated as a function learning problem using the PAC framework, analyzed three algorithms: column matching, combinatorial basis pursuit, and definite defectives.
result Derived bounds on the number of tests needed for approximate set identification, comparing with existing bounds and simulating performance.
A new sequential test for unnormalized densities.
problem Testing unnormalized densities with adaptive stopping.
method Sequential kernelized Stein discrepancy test, using non-uniform Stein kernels.
result Valid test with asymptotic lower bound for growth.
USP test improves on Pearson's chi-squared and G-test for independence.
problem Deficiencies in Pearson's chi-squared and G-test for independence. method USP test based on U-statistic estimator of population dependence measure. result USP test controls size, handles small cell counts, and detects minimal violations of independence.
AECF improves multimodal inference robustness and calibration.
problem Robustness and calibration issues in multimodal systems with missing inputs.
method Adaptive Entropy-Gated Contrastive Fusion (AECF) layer.
result Improves masked-input mAP by +18 pp at a 50% drop rate.
Deep neural nets optimize kernel parameters for non-parametric two-sample tests.
problem Determining if two samples come from the same distribution.
method Deep kernels trained to maximize test power, adapting to distribution smoothness and shape.
result Deep kernels outperform simpler kernels in high dimensions and complex data.
Paper tackles exposure bias in recommender systems using contrastive learning.
problem Exposure bias in large-scale recommender systems.
method Contrastive learning to reduce exposure bias via inverse propensity weighting.
result Contrastive learning effectively reduces exposure bias in recommender systems.
TESTED improves multi-domain stance detection with topic-guided sampling and contrastive learning.
problem Challenges in multi-domain stance detection due to domain-specific variations and imbalanced annotations.
method Topic-guided diversity sampling and contrastive learning objective.
result Significant improvement in F1 scores, up to 10.2 points out-of-domain.
We address the problem of non-parametric multiple model comparison: given l candidate models, decide whether each candidate is as good as the best one(s) or worse than it. We propose two statistical tests, each controlling a different notion of decision errors. The first test, building on the post selection inference…
A universal method for hypothesis tests and confidence sets without regularity conditions.
problem Difficult inference in irregular statistical models.
method Modified likelihood ratio statistic (split LRT).
result Works for any parametric and some nonparametric models.
Adversarial training achieves optimal test error for shallow networks.
problem Achieving optimal adversarial test error for general data distributions.
method Applying new Rademacher complexity bounds and properties of optimal adversarial predictors.
result Adversarial training can achieve optimal adversarial test error for general data distributions.
New method tests conditional independence using spectral representations.
problem Untestable conditional independence in many settings.
method Spectral representations of partial covariance operators, bi-level contrastive learning.
result Asymptotic validity and power guarantees for CI testing.
We propose a number of new algorithms for learning deep energy models and demonstrate their properties. We show that our SteinCD performs well in term of test likelihood, while SteinGAN performs well in terms of generating realistic looking images. Our results suggest promising directions for learning better models by …
A new permutation method improves two-sample testing power.
problem Two-sample testing with improved power and validity.
method Structured block-restricted cross-swaps.
result Block-restricted permutations achieve higher power than full permutations.
We test a historical price time series in a financial market (the NASDAQ 100 index) for a statistical property known as detailed balance. The presence of detailed balance would imply that the market can be modeled by a stochastic process based on a Markov chain, thus leading to equilibrium. In economic terms, a positiv…
Representations of probability measures in reproducing kernel Hilbert spaces provide a flexible framework for fully nonparametric hypothesis tests of independence, which can capture any type of departure from independence, including nonlinear associations and multivariate interactions. However, these approaches come wi…
A test for comparing networks using stochastic block models.
problem Determining if two network datasets come from the same model.
method Adopting stochastic block models, the study introduces an efficient algorithm to match estimated network parameters and develops a powerful test.
result The test is consistent and asymptotically follows a chi-squared distribution.
New method learns unbiased treatment representations from structured high-dimensional data.
problem Estimating causal effects from high-dimensional, structured treatments.
method Contrastive learning approach to learn unbiased treatment representations.
result The method identifies causal factors and discards non-causal ones, leading to unbiased causal effect estimates.
This paper applies combinatorial testing to machine learning for robust model performance.
problem Identifying robust machine learning models using test and training sets.
method Adapting combinatorial interaction testing for machine learning, focusing on simple features.
result Combinatorial coverage can enhance model performance and robustness.
Few-shot visual reasoning model learns analogical relationships from small data.
problem Training deep models on few samples for visual reasoning tasks.
method Meta-analogical contrastive learning to enforce structural similarity between training and test samples.
result Method outperforms state-of-the-art on RAVEN dataset with scarce training data.
Hypothesis testing in singular models is fundamentally about identifiable vs. non-identifiable parameters.
problem Testing in singular models is inherently problematic due to non-identifiability and degeneracy of Fisher information.
method Formalized the overlap obstruction and showed that hypotheses over non-identifiable parameters are untestable, while those over identifiable parameters reduce to classical testing.
result Hypotheses over non-identifiable parameters are untestable, while those over identifiable parameters reduce to classical testing.
Contrastive learning struggles with class collapse and feature suppression, revealing bias towards simpler solutions.
problem Contrastive learning struggles with class collapse and feature suppression, especially in supervised and unsupervised settings.
method Unified theoretical framework to determine which features are learnt by CL, revealing bias towards simpler solutions.
result Bias towards simpler solutions is a key factor in class collapse and feature suppression.
New method learns models to adapt to domain shifts at test time.
problem Learning models robust to distribution shifts in practical applications.
method Adaptive Risk Minimization (ARM) framework.
result Performance gains of 1-4% on image classification problems.
Proposes a framework for OOD detection combining multiple statistics.
problem Detecting out-of-distribution (OOD) samples reliably during inference.
method Multiple hypothesis testing with conformal p-values.
result Uniformly outperforms threshold-based tests across different datasets and neural networks.
Proposes a test for shared information between time series and events.
problem Detecting extreme events in time series data.
method Non-parametric statistical test using multiple two-sample testing at increasing lags.
result Outperforms or matches related tests on various datasets.
Study confirms fractional norms and quasinorms do not help overcome curse of dimensionality.
problem Overcoming the curse of dimensionality in machine learning.
method Systematic testing of fractional norms and quasinorms (p<1) on classification problems.
result Distance concentration behavior is qualitatively the same for all norms and quasinorms as dimensionality increases.
A new method detects distribution shifts faster than existing CTMs.
problem Detecting distribution shifts in data streams with contamination issues.
method Uses a fixed reference dataset to compare each new sample, avoiding contamination.
result Detects distribution shifts faster and more reliably than standard CTMs.
In clinical and neuroscientific studies, systematic differences between two populations of brain networks are investigated in order to characterize mental diseases or processes. Those networks are usually represented as graphs built from neuroimaging data and studied by means of graph analysis methods. The typical mach…
SimCLR pre-training improves CNN performance with fewer labels.
problem Learning with fewer labeled data.
method SimCLR contrastive learning method combined with supervised fine-tuning.
result SimCLR pre-training with supervised fine-tuning achieves almost optimal test loss with fewer labeled data.