This work provides guarantees for off-policy function estimation under realizability assumptions.
problem Estimating the value function of a policy under user-specified error-measuring distributions.
method The approach involves imposing a flexible regularization on the MIS objectives to account for an arbitrary user-specified distribution.
result Exact characterization of the optimal dual solution that determines the data-coverage assumption in the case of value-function learning.
Gaussian process regression helps approximate Bayesian inverse problems efficiently.
problem Computational intractability of Bayesian posterior distributions in inverse problems.
method Gaussian process regression to build a surrogate model for the likelihood.
result Error between true and approximate posterior can be bounded by weighted L2-norm error between true and approximate likelihood. Paper introduces a novel error measure for neural networks integrating statistical and information theory.
problem No single error measure is universally best for neural network training.
method Developed a novel error measure EExpAbs and integrated it into the Levenberg-Marquardt algorithm. result Self-adaptive, dynamic learning algorithm improves both model accuracy and training process.
Paper extends Bayesian Cramér-Rao bound with geometric considerations.
problem Estimation of covariance matrices with geometric structures.
method Intrinsic Bayesian Cramér-Rao bound with Riemannian geometry.
result Performance bounds for covariance matrix estimation.
Unified framework for FDR control in knockoffs, validating Gaussian knockoffs.
problem Asymptotic FDR control in knockoffs with user-specified distributions.
method Unified theoretical framework, three conditions on approximate knockoff statistics, Gaussian knockoffs generator based on moments matching.
result Gaussian knockoffs generator achieves asymptotic FDR control.
Enhances scenario approach for certifying design properties post-design.
problem Certifying additional useful properties in designs not considered during the design phase.
method Two-level framework of appropriateness: baseline and post-design. Distribution-free upper bounds on risk derived.
result Distribution-free upper bounds on the risk of failing to meet post-design appropriateness.
This paper studies how to capture dependency graph structures from real data which may not be Gaussian. Starting from marginal loss functions not necessarily derived from probability distributions, we utilize an additive over-parametrization with shrinkage to incorporate variable dependencies into the criterion. An ite…
Deep neural networks can generate any 2D distribution with high accuracy.
problem Generating accurate high-dimensional distributions from random noise.
method A deep neural network with a space-filling property of sawtooth functions.
result The network can approximate any 2D Lipschitz-continuous distribution arbitrarily closely.
Simplified GAN model shows how discriminator improves generalization.
problem Understanding GAN's generalization ability and avoiding memorization.
method Analyzing a simplified GAN model with early stopping and Wasserstein metric.
result Generalization error escapes from curse of dimensionality with early stopping.
Performance metrics (error measures) are vital components of the evaluation frameworks in various fields. The intention of this study was to overview of a variety of performance metrics and approaches to their classification. The main goal of the study was to develop a typology that will help to improve our knowledge a…
The paper develops methods to predict the probability of achieving a user goal in a task, ensuring the system alerts when the probability falls below a threshold.
problem Ensuring an autonomous system achieves the user's goal with calibrated probability estimates.
method Invertible conformal prediction using Probability-space Conformalized Quantile Regression (PCQR) to produce well-calibrated conditional prediction intervals.
result The method produces well-calibrated probabilities that the cumulative reward will fall within a user-specified target interval, with finite-sample guarantees.
We study the issue of PAC-Bayesian domain adaptation: We want to learn, from a source domain, a majority vote model dedicated to a target one. Our theoretical contribution brings a new perspective by deriving an upper-bound on the target risk where the distributions' divergence---expressed as a ratio---controls the tra…
SMI uses mixture models to improve SVGD's performance in Bayesian inference.
problem Variance collapse in SVGD for Bayesian inference, especially with small models.
method Generalizes SVGD to Stein mixture models, optimizing an ELBO lower bound.
result SMI avoids variance collapse and accurately estimates uncertainty for small BNNs.
Supporting evidence for adaptive feature program across diverse models.
problem Analyzing feature learning in neural networks.
method Over-parameterized sequence models and feature error measure (FEM).
result FEM is decreasing during training of adaptive feature models.
New method calibrates classifier probabilities with guaranteed coverage.
problem Inaccurate probability estimates by classifiers in high-risk applications.
method Adaptive temperature scaling algorithm for conformal prediction.
result Improves calibration error measures and standard metrics across various tasks.
Music SketchNet generates missing measures in incomplete music pieces, guided by user input.
problem Generating missing measures in incomplete monophonic musical pieces.
method Introducing SketchVAE for factorized representation of rhythm and pitch, and two discriminative architectures for guided music completion.
result Our approach outperforms state-of-the-art models in both objective and subjective evaluations.
We provide two main contributions in PAC-Bayesian theory for domain adaptation where the objective is to learn, from a source distribution, a well-performing majority vote on a different, but related, target distribution. Firstly, we propose an improvement of the previous approach we proposed in Germain et al. (2013), …
Memory-based models can learn to approximate Bayes-optimal predictors for non-stationary data.
problem Learning from non-stationary data with unobserved switching points.
method Memory-based neural models, including Transformers, LSTMs, and RNNs, trained to minimize log loss.
result Memory-based models can accurately approximate known Bayes-optimal algorithms and perform Bayesian inference over latent switching points.
The Statistical Learning Theory (SLT) provides the theoretical guarantees for supervised machine learning based on the Empirical Risk Minimization Principle (ERMP). Such principle defines an upper bound to ensure the uniform convergence of the empirical risk Remp(f), i.e., the error measured on a given data sample, to …
Stochastic kernel based dimensionality reduction approaches have become popular in the last decade. The central component of many of these methods is a symmetric kernel that quantifies the vicinity between pairs of data points and a kernel-induced Markov chain on the data. Typically, the Markov chain is fully specified…
Frengression models causal data flexibly and faithfully.
problem Challenges in robust benchmarking and evaluation of causal inference with real-world data.
method Introduces frengression, a deep generative model for joint distribution of covariates, treatments, and outcomes.
result Frengression provides accurate estimation and flexible simulation of multivariate, time-varying data.
Eye Movement analysis with Hidden Markov Models (EMHMM) is a method for modeling eye fixation sequences using hidden Markov models (HMMs). In this report, we run a simulation study to investigate the estimation error for learning HMMs with variational Bayesian inference, with respect to the number of sequences and the …
New method calibrates uncertainty estimates for image classifiers without labeled data.
problem Uncertainty estimates for modern classifiers are unreliable without labeled calibration data.
method Calibrates uncertainty estimates using unlabeled examples for distribution shifts.
result Proposes a method that provides excellent uncertainty estimates under natural distribution shifts.
EBUCB framework achieves optimal regret with bounded approximate inference error.
problem Theoretical gap between practical performance and theoretical justification of Bayesian bandit algorithms with approximate inference.
method Enhanced Bayesian Upper Confidence Bound (EBUCB) framework that accommodates bandit problems with approximate inference.
result EBUCB achieves optimal regret order O(logT) under certain conditions on inference error. SHADOWCAST generates graphs with user-specified attributes.
problem Controlling graph generation with understandable structures.
method Conditional generative adversarial network guided by Markov model.
result Competitive performance in generating desired graphs.
The paper introduces a method to control false splits in tree-based data aggregation.
problem Identifying the correct subgroups to treat as a single entity in tree-based data.
method Introduces the 'false split rate' and proposes a multiple hypothesis testing algorithm for tree-based aggregation.
result The proposed algorithm controls the false split rate, demonstrating its effectiveness on stock volatility and taxi fare data.
This paper proposes an active learning-based Gaussian process (AL-GP) metamodelling method to estimate the cumulative as well as complementary cumulative distribution function (CDF/CCDF) for forward uncertainty quantification (UQ) problems. Within the field of UQ, previous studies focused on developing AL-GP approaches…
Optimizes machine learning models while controlling risks.
problem Finding a model configuration that balances multiple conflicting metrics.
method Combines Bayesian Optimization with rigorous risk-controlling procedures.
result Identifies and selects Pareto optimal configurations with guaranteed risk levels.
Unified framework for distributional regret in bandits and reinforcement learning.
problem Characterizing the distribution of regret in multi-armed bandits and reinforcement learning.
method Unified framework with a UCBVI-style algorithm and distributional regret bounds.
result Distributional regret bounds with optimal trade-offs between expected and distributional regret.
New binary loss functions improve density ratio estimation accuracy.
problem Improving accuracy of density ratio estimators using binary classifiers.
method Characterized loss functions based on prescribed error measures in Bregman divergences.
result Novel loss functions prioritize accurate estimation of large density ratio values.
Efficiently constructs prediction bands with minimal assumptions.
problem Uncertainty quantification for nonparametric, heteroscedastic data.
method Semi-definite programming for data-adaptive prediction bands.
result Strong non-asymptotic coverage properties with minimal distributional assumptions.
Most classification methods provide either a prediction of class membership or an assessment of class membership probability. In the case of two-group classification the predicted probability can be described as "risk" of belonging to a "special" class . When the required output is a set of ordinal-risk groups, a discr…
Inspired by the unsupervised learning or self-organization in the machine learning context, here we attempt to draw `learning curve' for the collective behavior of job-seeking `zero-intelligence' labors in successive job-hunting processes. Our labor market is supposed to be opened especially for university graduates in…
We introduce the concept of coverage risk as an error measure for density ridge estimation. The coverage risk generalizes the mean integrated square error to set estimation. We propose two risk estimators for the coverage risk and we show that we can select tuning parameters by minimizing the estimated risk. We study t…
High dimensional data analysis is known to be as a challenging problem. In this article, we give a theoretical analysis of high dimensional classification of Gaussian data which relies on a geometrical analysis of the error measure. It links a problem of classification with a problem of nonparametric regression. We giv…
The clusters of a distribution are often defined by the connected components of a density level set. However, this definition depends on the user-specified level. We address this issue by proposing a simple, generic algorithm, which uses an almost arbitrary level set estimator to estimate the smallest level at which th…
JoLT uses LLMs to make probabilistic predictions on tabular data.
problem Making probabilistic predictions on tabular data efficiently and without preprocessing.
method JoLT leverages LLMs' in-context learning to define joint distributions over tabular data.
result JoLT outperforms other methods on tabular classification and regression tasks.
Contrastive learning adapts to data intrinsic dimensions, learning low-dimensional representations.
problem Learning high-dimensional representations from multi-modal data.
method Multi-modal contrastive learning with temperature optimization.
result Contrastive learning adapts to intrinsic dimensions of data, not specified dimensions.
ESS improves MCMC efficiency for correlated & multimodal distributions.
problem Slice Sampling's sensitivity to initial length scale and difficulty with correlated distributions.
method Adaptive tuning and parallel walkers for efficient sampling.
result ESS improves efficiency by more than an order of magnitude on correlated distributions.
Posterior conformal prediction improves prediction interval validity for subgroups.
problem Marginal and conditional prediction interval validity for subgroups.
method Modeling conditional nonconformity score distribution as a mixture of cluster distributions.
result PCP produces tighter prediction intervals, especially for well-represented clusters.
In this paper, we propose a one-pass algorithm on MapReduce for penalized linear regression \[f_λ(α, β) = \|Y - α\mathbf{1} - Xβ\|_2^2 + p_λ(β)\] where α is the intercept which can be omitted depending on application; β is the coefficients and pλ is the penalized function with penalizing parameter λ. $f_λ(α, β…
One of the challenging questions in time series forecasting is how to find the best algorithm. In recent years, a recommender system scheme has been developed for time series analysis using a meta-learning approach. This system selects the best forecasting method with consideration of the time series characteristics. I…
Develops statistical guarantees for image-to-image regression models.
problem Current image-to-image regression models lack statistical guarantees for model mistakes and hallucinations.
method Uncertainty quantification techniques with rigorous statistical guarantees for image-to-image regression problems.
result Derives uncertainty intervals around each pixel with formal mathematical guarantees.
Generative models learn distributions, new method finds inputs matching desired conditional distributions.
problem Designing inputs that produce specific conditional distributions, not just points.
method Conditional Distribution Matching (CDM) and MLGD-F algorithm.
result MLGD-F reliably recovers inputs matching diverse user-specified conditional distributions.
This text discusses several popular explanatory methods that go beyond the error measurements and plots traditionally used to assess machine learning models. Some of the explanatory methods are accepted tools of the trade while others are rigorously derived and backed by long-standing theory. The methods, decision tree…
We continue to develop our neural network (NN) based forecasting approach to anomaly detection (AD) using the Secure Water Treatment (SWaT) industrial control system (ICS) testbed dataset. We propose genetic algorithms (GA) to find the best NN architecture for a given dataset, using the NAB metric to assess the quality…
Lumbermark clusters data robustly, slicing limbs of mutual reachability trees.
problem Detecting clusters of varying sizes, densities, and shapes in datasets.
method Iteratively chops limbs of a mutual reachability minimum spanning tree.
result Lumbermark produces partitions with user-specified sizes.
ADS explains object differences by quantifying and removing underlying properties.
problem Explaining differences between two object images.
method Align-Deform-Subtract (ADS) framework that uses semantic alignments and iterative quantification/removal of differences.
result ADS provides disentangled error measures explaining object differences in terms of underlying properties.