Biography

I’m a PhD candidate and Vanier Scholar at the University of Toronto Department of Statistical Sciences working with professors Daniel Roy and Jeffrey Rosenthal on machine learning, online learning, and computational statistics.

Interests

  • Online Learning
  • Computational Statistics
  • Statistical Learning Theory
  • Applied Probability
  • Stochastic Analysis
  • Markov Chains

Education

  • PhD in Statistical Sciences, (Ongoing)

    University of Toronto

  • MSc in Statistical Sciences, 2017

    University of Toronto

  • BMath Mathematical Finance, 2014

    University of Waterloo

Publications

Jeffrey Negrea, Gintare Karolina Dziugaite, Daniel M Roy (2020). In Defense of Uniform Convergence: Generalization via derandomization with an application to interpolating predictors. Proceedings of the 37th International Conference on Machine Learning.

PDF

Jeffrey Negrea, Mahdi Haghifam, Gintare Karolina Dziugaite, Ashish Khisti, Daniel M Roy (2019). Information-Theoretic Generalization Bounds for SGLD via Data-Dependent Estimates. Advances in Neural Information Processing Systems 32.

PDF

Preprints

Blair Bilodeau, Jeffrey Negrea, Daniel M Roy (2020). Relaxing the I.I.D. Assumption: Adaptive Minimax Optimal Sequential Prediction with Expert Advice.

PDF

Mahdi Haghifam, Jeffrey Negrea, Ashish Khisti, Daniel M Roy, Gintare Karolina Dziugaite (2020). Sharpened Generalization Bounds based on Conditional Mutual Information and an Application to Noisy, Iterative Algorithms.

PDF

Jeffrey Negrea (2019). Optimal Scaling and Shaping of Random Walk Metropolis via Diffusion Limits of Block-IID Targets.

PDF

Jeffrey Negrea, Jeffrey S. Rosenthal (2017). Approximations of Geometrically Ergodic Markov Chains .

PDF