Logit-Coordinate models improve representation of mixed data types.
problem Representation of mixed continuous-categorical data in generative models.
method Logit-coordinate framework combining categorical and continuous variables.
result Logit-Coordinate models outperform one-hot encoding in simulations and real data.
Graph matching in noisy environments with Markovian errors.
problem Graph matching under time-dependent Markovian noise.
method Introduced edgelighter error model and analyzed graph matching thresholds.
result Graph matching thresholds and mixing times are of order Θ(n2logn) for Erdős-Rényi graphs, and O(nαlogn) for Stochastic Block Model graphs. Mix-n-Match improves uncertainty calibration in deep learning.
problem Post-hoc calibration of machine learning classifiers.
method Ensemble and composition strategies to improve accuracy, efficiency, and expressive power.
result Mix-n-Match strategies achieve better data-efficiency and expressive power while maintaining classification accuracy.
GLIMPS tackles abundant outlier detection in matched subspace detection.
problem Detecting matched subspaces in high-dimensional data with a high proportion of outliers.
method Two-stage approach combining greedy algorithm and mixed integer programming.
result GLIMPS can tolerate over 80% outliers, significantly outperforming state-of-the-art methods.
Mix and match networks enable image translation without paired data.
problem Image translation between domains or modalities with no direct paired data.
method Multiple encoders and decoders aligned for test-time composition.
result Model outperforms baselines in cross-modal image translation.
Develops a test for linear mixed models' fixed effects in high dimensions.
problem Understanding unobserved heterogeneity in high-dimensional models.
method Robust matching moment construction for adaptive sparse estimators of fixed effects.
result Consistent and unbiased test for high-dimensional models with constant cluster-level heterogeneity.
Score-based methods fail with isolated components and incorrect mixing proportions.
problem Score-based methods struggle with distributions having isolated components and incorrect mixing proportions.
method Score-based methods, including score matching, are used but fail in the presence of isolated components and incorrect mixing proportions.
result Score-based methods cannot discover isolated components or identify correct mixing proportions.
Proposes CDTD, a diffusion model for mixed-type tabular data.
problem Adapting diffusion models to mixed-type tabular data.
method Score matching and score interpolation for continuous features, adaptive noise schedules for categorical features.
result Consistently outperforms state-of-the-art models in mixed-type tabular data.
Mixed-size training improves CNN accuracy and speed.
problem Training CNNs on fixed image sizes limits their adaptability to various image sizes.
method Mixed-size training: training on multiple image sizes at once.
result Models trained with mixed-size images achieve higher accuracy and faster inference.
New online imputation method for mixed data improves accuracy and speed.
problem Missing value imputation in online settings for mixed data types.
method Online Gaussian copula model for imputation and change point detection.
result The model improves accuracy and speed, especially on large datasets.
iDEM generates samples from Boltzmann densities without data.
problem Generating statistically independent samples from unnormalized distributions.
method Iterative algorithm using energy and gradient for diffusion-based sampler training.
result iDEM achieves state-of-the-art performance and trains faster than existing methods.
A new method generates mixed-type features in tabular data with improved realism and accuracy.
problem Generating mixed-type features combining discrete and continuous data is challenging.
method A cascaded approach: first generates low-resolution categorical and coarse numerical features, then uses these in a high-resolution flow matching model.
result The model significantly improves detection scores, generating more realistic samples and capturing distributional details.
The aim of this paper is to provide a new method for learning the relationships between data that have been obtained independently. Unlike existing methods like matching, the proposed technique does not require any contextual information, provided that the dependency between the variables of interest is monotone. It ca…
A novel Bayesian approach for latent variable models from mixed data with missing values.
problem Learning parameters of latent variable models from mixed (continuous and ordinal) data with missing values.
method Proposes a novel Bayesian Gaussian copula factor (BGCF) approach that is consistent and robust to violations of certain conditions.
result BGCF substantially outperforms two state-of-the-art alternative approaches in simulations and is favorable over robust maximum likelihood (MLR) in practice.
Method generates i.i.d. samples from GT data using space-time mixing.
problem Generating synthetic i.i.d. samples from high-dimensional real-valued distributions.
method Space-time mixing strategies, diffusion bridges, and score-matching.
result Optimal transport from initial to target distribution.
Develops new tests for high-dimensional models with mixed signal strengths.
problem Challenges in testing models with many signals and high-dimensional data.
method Moment matching formulation for developing new tests.
result Demonstrates optimality of GRIP test for various model types.
Mix&Match framework speeds up RL agent training by bootstrapping from simpler agents.
problem Training complex reinforcement learning agents is slow and challenging.
method Automatically forms a curriculum over agents, progressively training more complex agents.
result Significant performance gains in diverse experimental setups.
The article proposes modified Gower's coefficients for handling mixed type variables in nearest neighbor methods.
problem Handling mixed type variables in nearest neighbor methods, especially imputation and statistical matching.
method Suggests modifications to the Gower's distance for interval and ratio scaled variables to address unbalanced contributions and outlier sensitivity.
result Improved distance calculations reduce the unbalanced contribution of different variable types and attenuate outlier effects.
Study on bandits with fading memory, improving regret bounds.
problem Stochastic multi-armed bandit problem with dependent samples.
method Developed a $\cC-$Mix Improved UCB algorithm and analyzed regret bounds in two scenarios.
result Regret bounds similar to independent case in slow mixing scenario, with an additive term.
The paper uses moment matching method for pricing spread options under Lévy models.
problem Pricing spread options under Lévy models with mean-variance mixture.
method Moment matching method applied to Lévy models with mean-variance mixture.
result Obtains semi-closed form formulas for spread option prices.
MALA mixes optimally in κ√d steps for log-concave sampling.
problem Sampling from log-concave distributions efficiently.
method Metropolis-Adjusted Langevin Algorithm (MALA) with warm start.
result Optimal minimax mixing time of κ√d iterations for log-concave distributions.
We consider the mixed regression problem with two components, under adversarial and stochastic noise. We give a convex optimization formulation that provably recovers the true solution, and provide upper bounds on the recovery errors for both arbitrary noise and stochastic noise settings. We also give matching minimax …
MixCIT tests conditional independence for mixed data types efficiently and reliably.
problem Testing conditional independence for mixed data types, especially when at least one is continuous.
method Graph-based test statistic comparing kernel similarities, debiased local-polynomial approach for continuous variables.
result Unified, efficient, and statistically guaranteed solution across heterogeneous data types.
We argue that the existing regret matchings for Nash equilibrium approximation conduct "jumpy" strategy updating when the probabilities of future plays are set to be proportional to positive regret measures. We propose a geometrical regret matching which features "smooth" strategy updating. Our approach is simple, intu…
OLS estimator nearly optimally identifies linear systems from single trajectory.
problem Identifying linear dynamical systems from a single observed trajectory.
method Generalized small-ball method for dependent data, avoiding mixing-time arguments.
result OLS estimator nearly matches minimax optimal performance for linear systems.
New algorithm learns optimal policy for average reward MDPs with sample complexity matching lower bound.
problem Learning optimal policy for average reward in uniformly ergodic MDPs.
method Developed an estimator with sample complexity of O(|S||A|t_{mix}ε^{-2}).
result First algorithm to match lower bound of existing literature.
Temporal Difference Learning analysis under non-i.i.d. data and nonlinear approximation.
problem Finite-sample behavior of TD(0) under non-i.i.d. data and nonlinear approximation.
method High-probability, finite-sample analysis of vanilla TD(0) on polynomially mixing Markov data, assuming Holder continuity and bounded generalized gradients.
result Bounds on the convergence rate of TD(0) with high probability, matching known i.i.d. rates and holding even with nonstationary initialization.
ReLU networks trained with MILPs match deep learning accuracy.
problem Training deep neural networks efficiently.
method Iterative training with Mixed Integer Linear Programs (MILPs).
result ReLU networks can be trained with MILPs achieving similar accuracy to deep learning methods.
Paper proposes deep neural networks for nonparametric regression from dependent data.
problem Nonparametric regression from strongly mixing observations.
method Minimum error entropy principle applied to deep neural networks.
result Deep neural networks achieve minimax optimal convergence rates for Gaussian errors.
Generalized Precision Matrix for scalable estimation of nonparametric Markov networks.
problem Estimating conditional independence structure in general distributions for all data types.
method Generalized Precision Matrix (GPM) for mixed-type variables, regularized score matching framework for scalability.
result Validated theoretical results and demonstrated scalability in various settings.
Proposes a bandit framework for dynamic user incentives.
problem Designing personalized incentives for users with evolving preferences.
method Combines greedy matching, UCB, and Markov chain theory.
result Algorithm provides theoretical regret bounds and practical examples.
This paper investigates the supervised learning problem with observations drawn from certain general stationary stochastic processes. Here by \emph{general}, we mean that many stationary stochastic processes can be included. We show that when the stochastic processes satisfy a generalized Bernstein-type inequality, a u…
Algorithm finds best mixture of training datasets for improved validation performance.
problem Learning from mixture distributions with covariate shift.
method Combines SGD with optimistic tree search and model re-use over mixture space.
result Proves simple regret guarantees for recovering optimal mixture.
Algorithm solves two-sided matching markets with unknown preferences and constraints.
problem Two-sided online matching markets with complementary preferences and quota constraints.
method Formulated as a bandit learning problem, proposed MMTS algorithm combining Thompson Sampling and double matching.
result MMTS achieves stability and linear Bayesian regret with respect to quota and time horizon.
New method recovers causal DAGs from general environments without strict assumptions.
problem Recovering causal DAGs from real-world data with varying distributions.
method Formalizes desiderata for causal representation learning in general environments, leveraging sufficient change conditions up to third-order derivatives.
result Fully recovers latent DAG and identifies latent variables up to minor indeterminacies under nonparametric mixing.
Study uses complex networks and machine learning to predict soccer match outcomes.
problem Predicting soccer match outcomes with complex networks and machine learning.
method Complex network metrics and match statistics were used to build machine learning models.
result Models based on passing networks were as effective as traditional models using match statistics.
The paper tackles long-context linear system identification with improved sample complexity bounds.
problem Identifying dynamical systems with long dependencies over fixed context windows.
method Established sample complexity bounds for systems with linear dependencies over a context window of length p.
result The learning process is not hindered by slow mixing properties in extended context windows.
ILTS iteratively refines linear regression models on subsets of data.
problem Linear regression with corruptions and outliers.
method Iteratively selects and refits the subset of samples with lowest loss.
result ILTS converges linearly to the closest mixture component under certain conditions.
New estimator for overlapping community detection in graphs.
problem Reconstructing community relations in graphs with overlapping memberships.
method Proposes a new estimator for Mixed-Membership Stochastic Block Model (MMSB) under diverging spiked eigenvalues condition.
result New estimator matches theoretical minimax lower bound on estimation error.
New bounds for mixing time and privacy in projected Langevin algorithm and noisy SGD.
problem Analyzing mixing times and privacy in projected Langevin algorithm and noisy SGD.
method New bounds derived using PABI framework and optimization problems.
result New bounds for mixing time and privacy in projected Langevin algorithm and noisy SGD, showing dependency on gradient regularity.
Graph curvature measured by inverse resistance distance.
problem Defining and analyzing curvature in graphs.
method Defining curvature via inverse resistance distance and proving properties.
result Graphs with positive curvature have controlled diameter and spectral properties.
The paper tackles deep learning from dependent data, achieving optimal performance.
problem Deep learning from strongly mixing observations, especially with regularization and optimality.
method Sparse-penalized regularization for deep neural networks, oracle inequality for expected excess risk.
result Deep neural network estimator achieves minimax optimal rate for nonparametric autoregression.
Mixed-precision CA-SGD for generalized linear models on GPUs
problem SGD communication bottleneck
method Mixed-precision CA-SGD
result Matches FP32 SGD loss within 0.5% on various problems
Study optimal and instance-dependent guarantees for solving linear equations with Markovian data.
problem Approximately solving linear fixed point equations with Markovian data.
method Non-asymptotic bounds and instance-dependent characterizations for stochastic approximation.
result Instance-optimality of the averaged SA estimator and matching upper and lower bounds.
The paper explores game-theoretic alignment of LLMs with human preferences, finding limitations and conditions.
problem Aligning LLMs with human preferences using game theory.
method Systematic study of payoff choices in a two-player zero-sum game for desirable alignment properties.
result Impossibility of preference matching in game-theoretic LLM alignment under standard assumptions.
Study on sparse recovery with mixed-quality data, establishing sample-size conditions.
problem Sparse recovery with heterogeneous noise from high- and low-quality sources.
method Establishes linear trade-off for sufficient conditions, analyzes LASSO algorithm.
result Linear trade-off for sufficient conditions, robustness of LASSO to data heterogeneity.
Study finds the minimum number of finite Gaussian mixtures for best approximation.
problem Finding the minimum number of finite Gaussian mixtures for best approximation.
method Local moment matching for upper bound and spectral analysis for lower bound.
result Corrects a previous lower bound in the case of Gaussian mixing distributions.
New algorithm separates audio sources better using alpha-stable distributions.
problem Improving audio source separation using complex distributions.
method Estimating mixtures of alpha-stable distributions using characteristic function matching.
result Better separation performance than Gaussian-based methods.