no code implementations • 16 Jun 2023 • Moïse Blanchard, Junhui Zhang, Patrick Jaillet
We propose a family of recursive cutting-plane algorithms to solve feasibility problems with constrained memory, which can also be used for first-order convex optimization.
no code implementations • 9 Feb 2023 • Moïse Blanchard, Junhui Zhang, Patrick Jaillet
For the feasibility problem, in which an algorithm only has access to a separation oracle, we show a stronger trade-off: for at most $d^{2-\delta}$ memory, the number of queries required is $\tilde\Omega(d^{1+\delta})$.
no code implementations • 9 Mar 2022 • Moïse Blanchard, Patrick Jaillet
In addition, our analysis also provides a learning rule for mean estimation in general metric spaces that is consistent under adversarial responses without any moment conditions on the sequence, a result of independent interest.
no code implementations • 16 Jan 2022 • Moïse Blanchard
We further show that k-nearest neighbor algorithm (kNN) is not optimistically universal and present a novel variant of 1NN which is optimistically universal for general input and value spaces in both strong and weak setting.
no code implementations • 29 Dec 2021 • Moïse Blanchard, Romain Cosson
However, when the loss function is bounded, the class of processes admitting strong universal consistency is much richer and its characterization could be dependent on the response setting (Hanneke).