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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
Slice Sampling has emerged as a powerful Markov Chain Monte Carlo algorithm that adapts to the characteristics of the target distribution with minimal hand-tuning. However, Slice Sampling's performance is highly sensitive to the user-specified initial length scale hyperparameter and the method generally struggles with …
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.
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…
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.
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.
A new algorithm for time series prediction intervals.
problem Non-exchangeability in time series data.
method Adaptive re-estimation of non-conformity scores.
result Significant reduction in interval width compared to existing methods.
Conformal prediction provides distribution-free uncertainty quantification for black-box models.
problem Uncertainty quantification for high-risk machine learning applications.
method Conformal prediction creates valid uncertainty sets without distributional assumptions.
result Sets contain the ground truth with a specified probability, e.g., 90%.
The paper proposes a method to reliably select design algorithms for machine learning-guided design tasks.
problem Choosing the right design algorithm for machine learning-guided design tasks.
method Combining designs' predicted property values with held-out labeled data to reliably forecast characteristics of the label distributions produced by different design algorithms.
result The method is guaranteed to return design algorithms that yield successful label distributions.
Paper explores fair classification with bounded disparity using finite datasets.
problem Ensuring fairness in binary classification with protected groups.
method Minimax optimal approach with fairness constraints and demographic disparity control.
result Proposes FairBayes-DDP+ method that achieves minimax lower bound on fairness-aware excess risk.
Hidden Markov models (HMMs) are one of the most widely used statistical methods for analyzing sequence data. However, the reporting of output from HMMs has largely been restricted to the presentation of the most-probable (MAP) hidden state sequence, found via the Viterbi algorithm, or the sequence of most probable marg…
WALNUTS improves sampling efficiency and robustness for multi-scale distributions.
problem Adapting leapfrog step size for multi-scale posterior distributions.
method Adapts leapfrog step size at fixed intervals of simulated time, selecting the largest step size to keep energy error below a threshold.
result Substantial improvements in sampling efficiency and robustness compared to standard NUTS.
Extends conformal prediction to contrastive learning for better coverage of positive samples.
problem Lack of principled guarantees on coverage in contrastive learning.
method Introduces minimum-volume covering sets with learnable constraints.
result Improves inclusion-exclusion trade-offs in positive and negative samples.
MACI improves LLM factuality inference with higher retention and lower time cost.
problem Ensuring factuality in LLM responses for high-stakes domains.
method Reformulated conformal inference in a multiplicative filtering setting, leveraging ensembles for more accurate factuality scores and group-conditional calibration.
result MACI achieves higher retention and lower time cost compared to baselines, preserving validity through group-conditional calibration.
Method predicts NAFLD risk with high accuracy and distribution-free coverage guarantees.
problem Insufficient population-level screening tools for NAFLD.
method Gradient-boosted decision trees with conformal prediction.
result Method achieves AUROC of 0.912 internally and 0.891 externally, superior to other models.
Common statistical prediction models often require and assume stationarity in the data. However, in many practical applications, changes in the relationship of the response and predictor variables are regularly observed over time, resulting in the deterioration of the predictive performance of these models. This paper …
ConfHit provides valid guarantees for generative models without oracle access.
problem Reliable guarantees for novel candidate generation in generative models.
method Formalizes certification and refinement of generated sets, leveraging weighted exchangeability and density-ratio weighted conformal p-values.
result Consistently delivers valid coverage guarantees and compact certified sets across various generative tasks.
We describe a novel binary classification technique called Banded SVM (B-SVM). In the standard C-SVM formulation of Cortes et al. (1995), the decision rule is encouraged to lie in the interval [1, \infty]. The new B-SVM objective function contains a penalty term that encourages the decision rule to lie in a user specif…
Risk control improves EENNs to make faster predictions without sacrificing accuracy.
problem Determining safe times for EENNs to exit early without degrading performance.
method Adapting risk control frameworks to EENNs to tune their exiting mechanism.
result Risk control enables EENNs to make faster predictions while maintaining user-specified performance goals.
The paper offers a method to create prediction sets with uncertainty control.
problem Calibrating and communicating uncertainty in machine learning predictions.
method Distribution-free, risk-controlling prediction sets using a holdout set to calibrate set sizes.
result Explicit finite-sample guarantees for error control in various machine learning tasks.
Learned optimizers trained on many tasks improve model training efficiency and generalization.
problem Training models efficiently and effectively with minimal user intervention.
method Developed a neural network-based hierarchical optimizer trained on thousands of tasks.
result The learned optimizers generalize better to unseen tasks and exhibit unique behaviors.
This paper addresses the challenges in classifying textual data obtained from open online platforms, which are vulnerable to distortion. Most existing classification methods minimize the overall classification error and may yield an undesirably large type I error (relevant textual messages are classified as irrelevant)…
We propose learning deep models that are monotonic with respect to a user-specified set of inputs by alternating layers of linear embeddings, ensembles of lattices, and calibrators (piecewise linear functions), with appropriate constraints for monotonicity, and jointly training the resulting network. We implement the l…
AutoCP automates the construction of accurate prediction intervals.
problem Creating valid and accurate prediction intervals for machine learning models.
method AutoML framework that optimizes prediction interval length for better accuracy and less conservatism.
result AutoCP significantly outperforms benchmark algorithms in constructing accurate prediction intervals.
The paper improves recommendation systems by ensuring their outputs are reliable.
problem Recommendation systems often lack reliability guarantees for their outputs.
method The method uses a pre-trained ranking model to create a set of items with rigorous FDR control.
result The approach provides a way to guarantee the reliability of recommendation outputs.
JAWS audits predictive uncertainty under covariate shift using jackknife+ weighted methods.
problem Auditing predictive uncertainty under data distribution shifts.
method JAW and JAWA methods for distribution-free uncertainty quantification.
result JAW relaxes the jackknife+'s assumption of data exchangeability for covariate shift.
The paper proposes a method to construct well-calibrated prediction sets for correlated target variables.
problem Constructing well-calibrated prediction sets for correlated target variables.
method The method uses vine copulas to estimate the joint cumulative distribution function of non-conformity scores and improves the asymptotic efficiency of the quantile estimate.
result The method guarantees asymptotically exact coverage and competitive efficiency on real-world regression problems.
This paper describes a suite of algorithms for constructing low-rank approximations of an input matrix from a random linear image of the matrix, called a sketch. These methods can preserve structural properties of the input matrix, such as positive-semidefiniteness, and they can produce approximations with a user-speci…
ScoreStop uses gradient tests to stop gradient boosting early.
problem Overfitting in gradient boosted decision trees.
method ScoreStop uses a functional score test based on gradients to stop boosting.
result ScoreStop is competitive with loss-based early stopping methods.
Enhances statistical inference using synthetic data.
problem Limited labeled data for statistical inference.
method GESPI framework that combines synthetic and real data.
result Error rate remains below a user-specified bound and decreases with synthetic data quality.
C-SymmPI provides near-conditional coverage for structured data with group symmetries.
problem Establishing near-conditional coverage guarantees for structured data with group symmetries.
method Developed a framework C-SymmPI that achieves near-conditional coverage under general data structures with group symmetries.
result Near-conditional coverage guarantees for structured data with group symmetries.
We present SDA-Bayes, a framework for (S)treaming, (D)istributed, (A)synchronous computation of a Bayesian posterior. The framework makes streaming updates to the estimated posterior according to a user-specified approximation batch primitive. We demonstrate the usefulness of our framework, with variational Bayes (VB) …