About
 

Mikhail Yurochkin

Research Staff Member

Research Publications

Who they work with

Categories

Bayesian Modeling Causal Inference Federated Learning Optimal Transport

Mikhail is a research staff member at IBM Research AI in Cambridge. His research interests include Bayesian nonparametrics and scalable Bayesian inference. Recently he has also been working on optimal transport and fairness in AI. Before IBM, Mikhail completed PhD in statistics at the University of Michigan, advised by Prof. Long Nguyen. He received his bachelor degree in applied mathematics and physics from Moscow Institute of Physics and Technology.

Top Work

Topics are more meaningful than words. AI for comparative literature.

Topics are more meaningful than words. AI for comparative literature.

Natural Language Processing

Alleviating label switching with optimal transport

Alleviating label switching with optimal transport

Optimal Transport

Publications with the MIT-IBM Watson AI Lab

Learning Proximal Operators to Discover Multiple Optima
Learning Proximal Operators to Discover Multiple Optima
ICLR
 
Sampling with Mollified Interaction Energy Descent
Sampling with Mollified Interaction Energy Descent
ICLR
 
Understanding new tasks through the lens of training data via exponential tilting
Understanding new tasks through the lens of training data via exponential tilting
ICLR
 
Domain Adaptation meets Individual Fairness. And they get along
Domain Adaptation meets Individual Fairness. And they get along
NeurIPSAI Fairness
 
Calibrated Data-Dependent Constraints with Exact Satisfaction Guarantees
Calibrated Data-Dependent Constraints with Exact Satisfaction Guarantees
NeurIPS
 
Log-Euclidean Signatures for Intrinsic Distances Between Unaligned Datasets
Log-Euclidean Signatures for Intrinsic Distances Between Unaligned Datasets
ICML
 
Measuring the robustness of Gaussian processes to kernel choice
Measuring the robustness of Gaussian processes to kernel choice
AISTATS
 
Post-processing for Individual Fairness
Post-processing for Individual Fairness
NeurIPS
 
On sensitivity of meta-learning to support data
On sensitivity of meta-learning to support data
NeurIPS
 
Model Fusion with Kullback–Leibler Divergence
Model Fusion with Kullback–Leibler Divergence
ICML
 
Two Simple Ways to Learn Individual Fairness Metrics from Data
Two Simple Ways to Learn Individual Fairness Metrics from Data
ICMLMachine Learning
 
SenSeI: Sensitive Set Invariance for Enforcing Individual Fairness
SenSeI: Sensitive Set Invariance for Enforcing Individual Fairness
ICLRMachine Learning
 
Individually Fair Gradient Boosting
Individually Fair Gradient Boosting
ICLRMachine Learning
 
Individually Fair Ranking
Individually Fair Ranking
ICLRAI Fairness
 
Statistical inference for individual fairness
Statistical inference for individual fairness
ICLRMachine Learning
 
Outlier-Robust Optimal Transport
Outlier-Robust Optimal Transport
ICML
 
Black Loans Matter: Fighting Bias for AI Fairness in Lending
Black Loans Matter: Fighting Bias for AI Fairness in Lending
AI FairnessAI in Finance
 
Continuous Regularized Wasserstein Barycenters
Continuous Regularized Wasserstein Barycenters
Optimal Transport
 
Does enforcing fairness mitigate biases caused by subpopulation shift?
Does enforcing fairness mitigate biases caused by subpopulation shift?
NeurIPS
 
Auditing ML Models for Individual Bias and Unfairness
Auditing ML Models for Individual Bias and Unfairness
AISTATSMachine Learning
 
SenSR: the first practical algorithm for individual fairness
SenSR: the first practical algorithm for individual fairness
AI FairnessRobustness
 
Layer-wise federated learning with FedMA
Layer-wise federated learning with FedMA
Federated Learning
 
Hierarchical Optimal Transport for Document Representation
Hierarchical Optimal Transport for Document Representation
NeurIPS
 
Statistical Model Aggregation via Parameter Matching
Statistical Model Aggregation via Parameter Matching
NeurIPS
 
Scalable inference of topic evolution via models for latent geometric structures
Scalable inference of topic evolution via models for latent geometric structures
NeurIPS
 
Topics are more meaningful than words. AI for comparative literature.
Topics are more meaningful than words. AI for comparative literature.
Natural Language ProcessingOptimal Transport
 
SPAHM: Parameter matching for model fusion
SPAHM: Parameter matching for model fusion
Bayesian Modeling
 
Using geometry to understand documents
Using geometry to understand documents
Natural Language Processing
 
Alleviating label switching with optimal transport
Alleviating label switching with optimal transport
Optimal Transport
 
Dirichlet Simplex Nest and Geometric Inference
Dirichlet Simplex Nest and Geometric Inference
ICML
 
Bayesian Nonparametric Federated Learning of Neural Networks
Bayesian Nonparametric Federated Learning of Neural Networks
Federated Learning