Algorithmic and Information Theoretic Methods in Data Science

Algorithmic & Information Theoretic Methods in Data Science (ECE6980)

Course home

Template for the Report

Possible Papers for Project

Please feel free to choose any other topics that you think is exciting, and is related to what we are doing in the class.

  • Communication Lower Bounds for Statistical Estimation Problems via a Distributed Data Processing Inequality, [pdf]
  • Statistical Algorithms and a Lower Bound for Detecting Planted Clique, [pdf]
  • Statistical Query Lower Bounds for Robust Estimation of High-dimensional Gaussians and Gaussian Mixtures, [pdf]
  • Extractor-Based Time-Space Lower Bounds for Learning, [pdf]
  • Algorithmic stability for adaptive data analysis, [pdf]
  • On Maximal Correlation, Hypercontractivity, and the Data Processing Inequality studied by Erkip and Cover, [pdf]
  • A Permutation-based Model for Crowd Labeling: Optimal Estimation and Robustness, [pdf]
  • Distributed Learning, Communication Complexity and Privacy, [pdf]
  • Distribution Testing Lower Bounds via Reductions from Communication Complexity, [pdf]
  • Tight Bounds for Communication-Assisted Agreement Distillation, [pdf]
  • Communication Complexity of Distributed Convex Learning and Optimization, [pdf]
  • Learning Graphical Models Using Multiplicative Weights, [pdf]
  • Neural networks and rational functions, [pdf]
  • A Stochastic PCA and SVD Algorithm with an Exponential Convergence Rate, [pdf]
  • Eigenvalue Decay Implies Polynomial-Time Learnability for Neural Networks, [pdf]
  • Computationally Efficient Robust Sparse Estimation in High Dimensions, [pdf]