SMAC3: A Versatile Bayesian Optimization Package for Hyperparameter Optimization.
Novel Min-Max Reformulations of Linear Inverse Problems.
Universal Approximation in Dropout Neural Networks.
On Generalizations of Some Distance Based Classifiers for HDLSS Data.
Decimated Framelet System on Graphs and Fast G-Framelet Transforms.
Near Optimality of Finite Memory Feedback Policies in Partially Observed Markov Decision Processes.
Empirical Risk Minimization under Random Censorship.
Scaling Laws from the Data Manifold Dimension.
Bayesian Multinomial Logistic Normal Models through Marginally Latent Matrix-T Processes.
LinCDE: Conditional Density Estimation via Lindsey's Method.
Bayesian Pseudo Posterior Mechanism under Asymptotic Differential Privacy.
Sampling Permutations for Shapley Value Estimation.
Theoretical Convergence of Multi-Step Model-Agnostic Meta-Learning.
Fast and Robust Rank Aggregation against Model Misspecification.
Accelerated Zeroth-Order and First-Order Momentum Methods from Mini to Minimax Optimization.
Optimal Transport for Stationary Markov Chains via Policy Iteration.
PAC Guarantees and Effective Algorithms for Detecting Novel Categories.
Optimality and Stability in Non-Convex Smooth Games.
LSAR: Efficient Leverage Score Sampling Algorithm for the Analysis of Big Time Series Data.
(f, Gamma)-Divergences: Interpolating between f-Divergences and Integral Probability Metrics.
Cascaded Diffusion Models for High Fidelity Image Generation.
SODEN: A Scalable Continuous-Time Survival Model through Ordinary Differential Equation Networks.
Inherent Tradeoffs in Learning Fair Representations.
Deep Learning in Target Space.
Active Learning for Nonlinear System Identification with Guarantees.
An improper estimator with optimal excess risk in misspecified density estimation and logistic regression.
Approximate Information State for Approximate Planning and Reinforcement Learning in Partially Observed Systems.
Innovations Autoencoder and its Application in One-class Anomalous Sequence Detection.
Approximation and Optimization Theory for Linear Continuous-Time Recurrent Neural Networks.
On Biased Stochastic Gradient Estimation.
Data-Derived Weak Universal Consistency.
XAI Beyond Classification: Interpretable Neural Clustering.
Structure-adaptive Manifold Estimation.
Recovering shared structure from multiple networks with unknown edge distributions.
Beyond Sub-Gaussian Noises: Sharp Concentration Analysis for Stochastic Gradient Descent.
Efficient MCMC Sampling with Dimension-Free Convergence Rate using ADMM-type Splitting.
DoubleML - An Object-Oriented Implementation of Double Machine Learning in Python.
Debiased Distributed Learning for Sparse Partial Linear Models in High Dimensions.
A Class of Conjugate Priors for Multinomial Probit Models which Includes the Multivariate Normal One.
Exploiting locality in high-dimensional Factorial hidden Markov models.
Evolutionary Variational Optimization of Generative Models.
Interpolating Predictors in High-Dimensional Factor Regression.
solo-learn: A Library of Self-supervised Methods for Visual Representation Learning.
MurTree: Optimal Decision Trees via Dynamic Programming and Search.
Solving Large-Scale Sparse PCA to Certifiable (Near) Optimality.
A Stochastic Bundle Method for Interpolation.
Overparameterization of Deep ResNet: Zero Loss and Mean-field Analysis.
Supervised Dimensionality Reduction and Visualization using Centroid-Encoder.
Joint Estimation and Inference for Data Integration Problems based on Multiple Multi-layered Gaussian Graphical Models.
Projected Statistical Methods for Distributional Data on the Real Line with the Wasserstein Metric.
Model Averaging Is Asymptotically Better Than Model Selection For Prediction.
Spatial Multivariate Trees for Big Data Bayesian Regression.
TFPnP: Tuning-free Plug-and-Play Proximal Algorithms with Applications to Inverse Imaging Problems.
Analytically Tractable Hidden-States Inference in Bayesian Neural Networks.
The correlation-assisted missing data estimator.
Toolbox for Multimodal Learn (scikit-multimodallearn).
Score Matched Neural Exponential Families for Likelihood-Free Inference.
