Ioannis Mitliagkas

Affiliations

MilaUniversity of Montreal

papers

618

total citations

papers (11)

Invariance Principle Meets Information Bottleneck for Out-of-Distribution Generalization

NEURIPS 2021arXiv

325

citations

In search of robust measures of generalization

NEURIPS 2020arXiv

104

citations

Stochastic Gradient Descent-Ascent and Consensus Optimization for Smooth Games: Convergence Analysis under Expected Co-coercivity

NEURIPS 2021arXiv

citations

Additive Decoders for Latent Variables Identification and Cartesian-Product Extrapolation

NEURIPS 2023arXiv

citations

Empirical Analysis of Model Selection for Heterogeneous Causal Effect Estimation

ICLR 2024arXiv

citations

Gradient Descent Is Optimal Under Lower Restricted Secant Inequality And Upper Error Bound

NEURIPS 2022arXiv

citations

CADet: Fully Self-Supervised Out-Of-Distribution Detection With Contrastive Learning

NEURIPS 2023arXiv

citations

Ioannis Mitliagkas

Affiliations

papers (11)

Invariance Principle Meets Information Bottleneck for Out-of-Distribution Generalization

In search of robust measures of generalization

Stochastic Gradient Descent-Ascent and Consensus Optimization for Smooth Games: Convergence Analysis under Expected Co-coercivity

Additive Decoders for Latent Variables Identification and Cartesian-Product Extrapolation

Empirical Analysis of Model Selection for Heterogeneous Causal Effect Estimation

Gradient Descent Is Optimal Under Lower Restricted Secant Inequality And Upper Error Bound

CADet: Fully Self-Supervised Out-Of-Distribution Detection With Contrastive Learning

Compositional Risk Minimization

Understanding Adam Requires Better Rotation Dependent Assumptions

No Wrong Turns: The Simple Geometry Of Neural Networks Optimization Paths

LEAD: Min-Max Optimization from a Physical Perspective

papers (11)

Invariance Principle Meets Information Bottleneck for Out-of-Distribution Generalization

In search of robust measures of generalization

Stochastic Gradient Descent-Ascent and Consensus Optimization for Smooth Games: Convergence Analysis under Expected Co-coercivity

Additive Decoders for Latent Variables Identification and Cartesian-Product Extrapolation

Empirical Analysis of Model Selection for Heterogeneous Causal Effect Estimation

Gradient Descent Is Optimal Under Lower Restricted Secant Inequality And Upper Error Bound

CADet: Fully Self-Supervised Out-Of-Distribution Detection With Contrastive Learning

Compositional Risk Minimization

Understanding Adam Requires Better Rotation Dependent Assumptions

No Wrong Turns: The Simple Geometry Of Neural Networks Optimization Paths

LEAD: Min-Max Optimization from a Physical Perspective