Birs- 24w5297: Mathematics of Deep Learning
-
Title: Yes, my deep network works! But.. what did it learn?
Speaker:
Link:
-
Title: Lecture I: White-Box Architecture Design via Unrolled Optimization and Compression
Speaker:
Link:
-
Title: Equivariant convolutional networks over arbitrary Lie groups
Speaker:
Link:
-
Title: A Precise High-Dimensional Statistical Theory for Convex and Nonconvex Matrix Sensing
Speaker:
Link:
-
Title: Constrained Reinforcement Learning
Speaker:
Link:
-
Title: Surprising phenomena of max-ℓ
Speaker:
Link:
-
Title: Learning Dynamics of Overparametrized Neural Networks
Speaker:
Link:
-
Title: Probably Approximately Correct in the Future.
Speaker:
Link:
-
Title: Gradient Descent and Attention Models: Challenges Posed by the Softmax Function
Speaker:
Link:
-
Title: Where within F_1 does gradient descent search?
Speaker:
Link:
-
Title: Data Reconstruction Attacks and Defenses: From Theory to Practice
Speaker:
Link:
-
Title: A Poincaré Inequality and Consistency Results for Signal Sampling on Large Graphs
Speaker:
Link:
-
Title: The Role of Sparsity in Differentially-Private Learning
Speaker:
Link:
-
Title: Symmetries in machine learning: point clouds and graphs.
Speaker:
Link:
-
Title: How many FLOPs is a token worth?
Speaker:
Link:
-
Title: Lazy quotient metrics: Approximate symmetries for ML models
Speaker:
Link:
-
Title: Robust Unrolled Networks
Speaker:
Link:
-
Title: Overcoming the Boundaries of Artificial Intelligence: A Mathematical Approach
Speaker:
Link: