Mladen Kolar is an Associate Professor of Econometrics and Statistics at the University of Chicago Booth School of Business. His research is focused on high-dimensional statistical methods, graphical models, varying-coefficient models and data mining, driven by the need to uncover interesting and scientifically meaningful structures from observational data.
Interests
- Statistical machine learning
- Probabilistic graphical models
- Dynamic networks estimation
- High-dimensional estimation and inference
- Stochastic optimization with constraints
- Distributed optimization and federated learning
Education
PhD in Machine Learning, 2013
Carnegie Mellon University
Diploma in Computer Engineering, 2006
University of Zagreb, Faculty of Electrical Engineering and Computing
Latest
- One Policy is Enough: Parallel Exploration with a Single Policy is Minimax Optimal for Reward-Free Reinforcement Learning
- Differentially Private Matrix Completion through Low-rank Matrix Factorization
- Provably training overparameterized neural network classifiers with non-convex constraints
- Fully Stochastic Trust-Region Sequential Quadratic Programming for Equality-Constrained Optimization Problems
- Gradient-Variation Bound for Online Convex Optimization with Constraints
- Local AdaGrad-type algorithm for stochastic convex-concave optimization
- Latent Multimodal Functional Graphical Model Estimation
- On the Lasso for Graphical Continuous Lyapunov Models
- Pessimism meets VCG: Learning Dynamic Mechanism Design via Offline Reinforcement Learning
- An adaptive stochastic sequential quadratic programming with differentiable exact augmented lagrangians
- Dynamic Regret Minimization for Control of Non-stationary Linear Dynamical Systems
- Personalized Federated Learning with Multiple Known Clusters
- A Nonconvex Framework for Structured Dynamic Covariance Recovery
- FuDGE: A Method to Estimate a Functional Differential Graph in a High-Dimensional Setting
- Joint Gaussian Graphical Model Estimation: A Survey
- L-SVRG and L-Katyusha with Adaptive Sampling
- Inference for high-dimensional varying-coefficient quantile regression
- Adaptive Client Sampling in Federated Learning via Online Learning with Bandit Feedback
- Two-sample inference for high-dimensional Markov networks
- Inequality Constrained Stochastic Nonlinear Optimization via Active-Set Sequential Quadratic Programming
- A Fast Temporal Decomposition Procedure for Long-horizon Nonlinear Dynamic Programming
- Robust Inference for High-Dimensional Linear Models via Residual Randomization
- Estimating differential latent variable graphical models with applications to brain connectivity
- High-dimensional Functional Graphical Model Structure Learning via Neighborhood Selection Approach
- High-dimensional Index Volatility Models via Stein's Identity
- Personalized Federated Learning: A Unified Framework and Universal Optimization Techniques
- Instrumental Variable Value Iteration for Causal Offline Reinforcement Learning
- Tensor Canonical Correlation Analysis With Convergence and Statistical Guarantees
- Provably Efficient Neural Estimation of Structural Equation Model: An Adversarial Approach
- Statistical Inference for Networks of High-Dimensional Point Processes
- Convergence Analysis of Accelerated Stochastic Gradient Descent under the Growth Condition
- Estimation of a Low-rank Topic-Based Model for Information Cascades
- Semiparametric Nonlinear Bipartite Graph Representation Learning with Provable Guarantees
- Posterior Ratio Estimation for Latent Variables
- Recovery of simultaneous low rank and two-way sparse coefficient matrices, a nonconvex approach
- Kernel meets sieve: post-regularization confidence bands for sparse additive model
- Simultaneous Inference for Pairwise Graphical Models with Generalized Score Matching
- Natural Actor-Critic Converges Globally for Hierarchical Linear Quadratic Regulator
- Constrained High Dimensional Statistical Inference
- Partially Linear Additive Gaussian Graphical Models
- Learning Influence-Receptivity Network Structure with Guarantee
- Convergent Policy Optimization for Safe Reinforcement Learning
- Direct Estimation of Differential Functional Graphical Models
- High-dimensional Varying Index Coefficient Models via Stein's Identity
- Distributed Stochastic Multi-Task Learning with Graph Regularization
- Joint Nonparametric Precision Matrix Estimation with Confounding
- Post-Regularization Inference for Time-Varying Nonparanormal Graphical Models
- Provable Gaussian Embedding with One Observation
- ROCKET: Robust confidence intervals via Kendall's tau for transelliptical graphical models
- Scalable Peaceman-Rachford Splitting Method with Proximal Terms
- Efficient Distributed Learning with Sparsity
- Sketching Meets Random Projection in the Dual: A Provable Recovery Algorithm for Big and High-dimensional Data
- An Influence-Receptivity Model for Topic based Information Cascades
- Recovering block-structured activations using compressive measurements
- Sketching meets random projection in the dual: a provable recovery algorithm for big and high-dimensional data
- The Expxorcist: Nonparametric Graphical Models Via Conditional Exponential Densities
- Uniform inference for high-dimensional quantile regression: linear functionals and regression rank scores
- Distributed Multi-Task Learning
- Distributed Multi-Task Learning with Shared Representation
- Discussion of ``Coauthorship and citation networks for statisticians''
- Inference for High-dimensional Exponential Family Graphical Models
- Statistical Inference for Pairwise Graphical Models Using Score Matching
- Learning structured densities via infinite dimensional exponential families
- Optimal variable selection in multi-group sparse discriminant analysis
- A General Framework for Robust Testing and Confidence Regions in High-Dimensional Quantile Regression
- Inference for Sparse Conditional Precision Matrices
- Mean and variance estimation in high-dimensional heteroscedastic models with non-convex penalties
- Optimal Feature Selection in High-Dimensional Discriminant Analysis
- Berry-Esseen bounds for estimating undirected graphs
- Graph Estimation From Multi-attribute Data
- Feature Selection in High-Dimensional Classification
- Markov Network Estimation From Multi-attribute Data
- Consistent Covariance Selection From Data With Missing Values
- Variance Function Estimation in High-dimensions
- Estimating Networks With Jumps
- Marginal Regression For Multitask Learning
- Minimax Localization of Structural Information in Large Noisy Matrices
- On Time Varying Undirected Graphs
- Statistical and computational tradeoffs in biclustering
- Union Support Recovery In Multi-task Learning
- Estimating Time-varying Networks
- On Sparse Nonparametric Conditional Covariance Selection
- Ultra-high Dimensional Multiple Output Learning With Simultaneous Orthogonal Matching Pursuit: Screening Approach
- Sparsistent Estimation Of Time-varying Discrete Markov Random Fields
- Sparsistent Learning Of Varying-coefficient Models With Structural Changes
- Time-varying Dynamic Bayesian Networks
- CSMET: Comparative Genomic Motif Detection via Multi-Resolution Phylogenetic Shadowing
- Computer-Aided document Indexing Systems