Seminar by Alexander Wein
Probability seminar series Alexander Wein Room: M3 3127 |
Is Planted Coloring Easier than Planted Clique?
Probability seminar series Alexander Wein Room: M3 3127 |
Is Planted Coloring Easier than Planted Clique?
Actuarial Science and Financial Mathematics seminar series Karim Barigou Room: M3 3127 |
Insurance valuation: a two-step generalized regression approach
Probability seminar series Mark Sellke Room: M3 3127 |
Algorithmic Thresholds for Spherical Spin Glasses
Statistics and Biostatistics seminar series Ehsan Karim Room: M3 3127 |
Rethinking Residual Confounding Bias Reduction: Why Vanilla hdPS Alone is No Longer Enough in the Era of Machine Learning
The Department of Statistics and Actuarial Science is very pleased to announce that it is hosting the Young Talents in Actuarial Science and Quantitative Finance conference from Thursday, April 27 to Friday, April 28, 2023. This conference brings together active junior research scholars in the Actuarial Science and Quantitative Finance communities to the University of Waterloo to exchange their cutting-edge research advances. Talks cover a diversified range of research topics addressing current challenges in insurance, risk management, and mathematical finance.
Probability seminar series Reza Gheissari Room: M3 3127 |
High-dimensional limit theorems for stochastic gradient descent
Actuarial Science and Financial Mathematics seminar series Arthur Charpentier Room: M3 3127 |
Causal Inference and Counterfactuals with Optimal Transport With Applications in Fairness and Discrimination
Statistics and Biostatistics seminar series Qingrun Zhang Room: M3 3127 |
Stabilized Core gene and Pathway Election uncovers pan-cancer shared pathways and a cancer-specific driver
Distinguished Lecture Series Vladimir Vovk Room: DC 1302 |
Nonparametric prediction and testing
The assumption of randomness (the data are generated in the IID fashion) is the key assumption used in machine learning and much of nonparametric statistics. My main topics will be prediction under this assumption and testing the assumption. The treatment of both topics will be based on the relatively recent technique of conformal prediction, but I will try to connect it with David A. Sprott's ideas and areas of research pointing out some paradoxical features of prediction and testing in the framework of unrestricted randomness. On one hand, they are barely possible, in the sense that the existence of non-trivial prediction and testing procedures is fragile: they cease to exist when the problem settings are modified in natural ways. On the other, such procedures can be highly efficient in realistic situations; I will give both theoretical and experimental results demonstrating this.
Statistics and Biostatistics seminar series Elena Tuzhilina Room: M3 3127 |
Statistical curve models for inferring 3D chromatin architecture