Birs- 16w5136: Applied Harmonic Analysis, Massive Data Sets, Machine Learning, and Signal Processing
-
Title: Obstacles to AI, Mathematical and Otherwise
Speaker:
Link:
-
Title: Fundamental limits and algorithms for recovery under matrix spike models
Speaker:
Link:
-
Title: Deep vs. shallow networks
Speaker:
Link:
-
Title: Robust Low-rank Modeling for High-dimensional and Massive Datasets
Speaker:
Link:
-
Title: Regularized Nonlinear Acceleration
Speaker:
Link:
-
Title: Convex (and tractable?) formulations for single hidden layer neural networks
Speaker:
Link:
-
Title: Functional Maps and Functional Map Networks for Joint Data Analysis
Speaker:
Link:
-
Title: Provable Approximations of Deep Nets
Speaker:
Link:
-
Title: Multimodal signal processing using Alternating Diffusion
Speaker:
Link:
-
Title: The discrete sign problem: uniqueness, stable recovery and phase retrieval applications
Speaker:
Link:
-
Title: Rapid, robust and reliable blind deconvolution via nonconvex optimization
Speaker:
Link:
-
Title: Cascaded gain control representations
Speaker:
Link:
-
Title: The Deceptive Nature of Generalization in Machine Learning
Speaker:
Link:
-
Title: Nonconvex Recovery of Low-Complexity Models
Speaker:
Link:
-
Title: Universality laws for randomized dimension reduction
Speaker:
Link:
-
Title: Clustering subgaussian mixtures via semidefinite programming
Speaker:
Link:
-
Title: Synchronization over Cartan motion groups via contraction
Speaker:
Link:
-
Title: Batched Stochastic Gradient Descent with Weighted Sampling
Speaker:
Link:
-
Title: Phase Retrieval
Speaker:
Link:
-
Title: Simultaneous Alignment and Classification - A Representation Theory Perspective
Speaker:
Link: