Reading Group · Summer 2026

Theory of Generalization Reading Group

A reading group on why modern neural networks generalize despite overparameterization, interpolation, and their ability to fit random labels.

Overview

This reading group asks why modern neural networks generalize despite being highly overparameterized, capable of fitting random labels, and often trained far beyond interpolation. We follow the story from classical statistical learning theory to the empirical puzzles that challenged it, including double descent and benign overfitting, then examine proposed explanations based on implicit bias, Bayesian and PAC-Bayes perspectives, compression, grokking, and sparse subnetworks.

Across the sessions, the guiding question is: which parts of deep-learning generalization are now understood, and which phenomena still require new theory?

Schedule

Next topic
Why Does Gradient Descent Generalize, and Why Can SGD Generalize Better?
08 Jul 2026 · Generalization through stable minima, flat minima, and the noise-induced bias of SGD.

Schedule and readings may change as the group evolves. Slides will be added when available.

DateTopicReadingsSlides
03 Jun 2026
Classical theory of generalization
VC dimension, Rademacher complexity, uniform convergence.
Understanding Machine Learning, Part I selections. Slides
10 Jun 2026
Understanding Deep Learning Requires Rethinking Generalization
Random labels, interpolation, and whether VC dimension is the wrong notion of complexity.
Zhang et al., 2017 Slides
17 Jun 2026
Double Descent and Benign Overfitting
Why can test error decrease again after interpolation?
Reconciling modern machine-learning practice and the classical bias-variance trade-off Slides
24 Jun 2026
Implicit Bias and Soft Inductive Biases
Implicit regularization, SGD bias, simplicity preferences, and soft inductive biases.
Implicit Bias of Gradient Descent on Separable Data
Bayesian Deep Learning and a Probabilistic Perspective of Generalization
Averaging Weights Lead to Wider Optima and Better Generalization
TBA
03 Jul 2026
Compression, Nonuniform Learnability, and PAC-Bayes
Can compression and PAC-Bayes explain why deep networks generalize? Simple functions can occupy exponentially larger regions of parameter space, making them easier for learning algorithms to find and providing a compelling account of generalization in DNNs.
A PAC-Bayesian Approach to Spectrally-Normalized Margin Bounds for Neural Networks Slides
08 Jul 2026
Why Does Gradient Descent Generalize, and Why Can SGD Generalize Better?
Generalization through stable minima: gradient-based methods can be biased toward stable, flat regions of the loss landscape, and flat minima are known to generalize well. We discuss how SGD noise may strengthen this bias relative to full-batch gradient descent.
Train Faster, Generalize Better: Stability of Stochastic Gradient Descent
Towards Understanding Generalization of Deep Learning: Perspective of Loss Landscapes
TBA
15 Jul 2026 Tentative invited talk
Do LLMs actually generalize?
PAC/VC bounds, overparameterization, compression, simplicity, and LLM generalization.
Non-Vacuous Generalization Bounds for Large Language Models
Unlocking tokens as data points for generalization bounds on larger language models
TBA
22 Jul 2026 Open discussion
Grokking: Generalization Beyond Overfitting
Does grokking support or challenge the view that deep learning is not so mysterious?
Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets
Grokking as the Transition from Lazy to Rich Training Dynamics
TBA
29 Jul 2026 Tentative invited talk
Lottery Ticket Hypothesis
Do neural networks succeed because training discovers sparse winning tickets?
The Lottery Ticket Hypothesis TBA

Organizer

Organized by Abir Harrasse at the Jinesis AI Lab, University of Toronto.