Causal inference Probabilistic machine learning Graph neural networks Cognitive science
Large Language Models: Safety in LLMs Applied Probability: Stochastic Control, Optimal Transport, Generative Flow Networks AutoML: Pruning, Neural Architecture Search
Federated Learning Optimization Distributed Computing
Convex optimization Stochastic optimization High-order optimization Machine learning
Convex Optimization Online Learning
Distributed machine learning, Optimization, Communication Systems
Machine learning, Optimization
Statistical Physics, Optimization, Information theory
Deep learning, Over-parametrized models
Machine Learning
Mathematical optimization, Statistics and Applications
Applied deep learning, Optimization techniques, Casual Inference, Computational Neuroscience, Language Representation, Statistical Sampling Techniques
Machine Learning, Gaussian Processes
Machine Learning, Compressive Sensing
Generative model, Deep learning, Inverse problem
Statistical Physics and Electronic Information, Spin Glass Theory and Information Theory.
Bayesian optimization Machine Learning Causality Neuroscience
Research Interests: Optimization Algorithms and Randomness.
nternship project topic: Reinforcement Learning on Networks
Internship project topic:
Internship project topic: Storage-optimal continuous optimization
Internship project topic: Projection-Free Adaptive Convex Optimization
Internship project topic: Learning-based Compressive Sensing for dynamic MRI
Internship project topic: Stochastic three-operator splitting method via variance reduction.
Internship project topic: Robust submodular maximization, submodularity in non-convex optimization.
Internship project topic: Molecular energy prediction using coulomb, wavelet and scattering representations. Spectral optimizers for gradient descent.
Internship project topic: Bayesian Optimization
Internship project topic: Alternating Minimisation
Internship project topic: Theoretical guarantees for optimization algorithms Quantum tomography
Internship project topic: Theoretical guarantees for M-estimators in high dimension Matrix completion
Internship project topic: Group Sparse Models and Submodular function theory.
Internship project topic: Efficient sampling and compression of ensembles of intracortical EEG signals
Internship project topic: Graphical modeling of brain connections and random matrix theory for applications in linear inverse problems.
Internship project topic: Active sampling for digital confocal microscopy.
Internship project topic: Structured sparsity with shearlets as sparsifying basis for Compressive Sensing
Internship project topic: Convex model-based signal recovery via expander matrices.
Internship project topic: Matrix completion.
Internship project topic: Sparse Covariance Selection and Phase-retrieval.
Internship project topic: Analysis of structured sparse signals using Linear Programming.
Internship project topic: Low dimensional models for high dimensional data.
Internship project topic: Discrete Structured Sparsity Models and Dynamic Programming.
Internship project topic: Synthesis and atomic norm formulation equivalence for sparse signal recovery.
Internship project topic: Sparse Data Analysis.