generalization of linearized neural networks staircase
play

Generalization of linearized neural networks: staircase decay and - PowerPoint PPT Presentation

Mar 18, 2023 •557 likes •1.3k views

Generalization of linearized neural networks: staircase decay and double descent Song Mei UC Berkeley July 23, 2020 Department of Mathematics, HKUST Deep Learning Revolution Machine translation Autonomous Vehicle Robotics Healthcare

  1. Generalization of linearized neural networks: staircase decay and double descent Song Mei UC Berkeley July 23, 2020 Department of Mathematics, HKUST

  2. Deep Learning Revolution Machine translation Autonomous Vehicle Robotics Healthcare Gaming Deep learning Communication Finance

  3. Deep Learning Revolution Machine translation Autonomous Vehicle Robotics Healthcare Gaming Deep learning Communication Finance “ACM named Yoshua Bengio, Geoffrey Hinton, and Yann LeCun recipients of the 2018 ACM A.M. Turing Award for conceptual and engineering breakthroughs that have made deep neural networks a critical component of computing. ”

  4. But theoretically?

  5. But theoretically? WHEN and WHY does deep learning work?

  6. Call for Theoretical understandings “Alchemy”

  7. Call for Theoretical understandings “Alchemy” Science Reproducible Physical Mathematical Experiments Laws Theories

  8. ✩ ✩ What don’t we understand?

  9. ✩ ✩ What don’t we understand? Empirical Surprises [Zhang, et.al, 2015]: ◮ Over-parameterization: ★ parameters ✢ ★ training samples. ◮ Non-convexity. ◮ Efficiently fit all the training samples using SGD. ◮ Generalize well on test samples.

  10. What don’t we understand? Empirical Surprises [Zhang, et.al, 2015]: ◮ Over-parameterization: ★ parameters ✢ ★ training samples. ◮ Non-convexity. ◮ Efficiently fit all the training samples using SGD. ◮ Generalize well on test samples. Mathematical Challenges ✩ Non-convexity Why efficient optimization? ✩ Over-parameterization Why effective generalization?

  11. A gentle introduction to Linearization theory of neural networks

  12. Linearized neural networks (neural tangent model) ◮ Multi-layers neural network ❢ ✭ x ❀ θ ✮ , x ✷ R ❞ , θ ✷ R ◆ ❢ ✭ x ❀ θ ✮ ❂ W ▲ ✛ ✭ ✁ ✁ ✁ W ✷ ✛ ✭ W ✶ x ✮✮ ✿ ◮ Linearization around (random) parameter θ ✵ ❢ ✭ x ❀ θ ✮ ❂ ❢ ✭ x ❀ θ ✵ ✮ ✰ ❤ θ � θ ✵ ❀ r θ ❢ ✭ x ❀ θ ✵ ✮ ✐ ✰ ♦ ✭ ❦ θ � θ ✵ ❦ ✷ ✮ ✿ ◮ Neural tangent model: the linear part of ❢ ❢ NT ✭ x ❀ β ❀ θ ✵ ✮ ❂ ❤ β ❀ r θ ❢ ✭ x ❀ θ ✵ ✮ ✐ ✿ [Jacot, Gabriel, Hongler, 2018] [Chizat, Bach, 2018b]

  13. Linearized neural networks (neural tangent model) ◮ Multi-layers neural network ❢ ✭ x ❀ θ ✮ , x ✷ R ❞ , θ ✷ R ◆ ❢ ✭ x ❀ θ ✮ ❂ ✛ ✭ W ▲ ✛ ✭ ✁ ✁ ✁ W ✷ ✛ ✭ W ✶ x ✮✮✮ ✿ ◮ Linearization around (random) parameter θ ✵ ❢ ✭ x ❀ θ ✮ ❂ ❢ ✭ x ❀ θ ✵ ✮ ✰ ❤ θ � θ ✵ ❀ r θ ❢ ✭ x ❀ θ ✵ ✮ ✐ ✰ ♦ ✭ ❦ θ � θ ✵ ❦ ✷ ✮ ✿ ◮ Neural tangent model: the linear part of ❢ ❢ NT ✭ x ❀ β ❀ θ ✵ ✮ ❂ ❤ β ❀ r θ ❢ ✭ x ❀ θ ✵ ✮ ✐ ✿ [Jacot, Gabriel, Hongler, 2018] [Chizat, Bach, 2018b]

  14. Linearized neural networks (neural tangent model) ◮ Multi-layers neural network ❢ ✭ x ❀ θ ✮ , x ✷ R ❞ , θ ✷ R ◆ ❢ ✭ x ❀ θ ✮ ❂ ✛ ✭ W ▲ ✛ ✭ ✁ ✁ ✁ W ✷ ✛ ✭ W ✶ x ✮✮✮ ✿ ◮ Linearization around (random) parameter θ ✵ ❢ ✭ x ❀ θ ✮ ❂ ❢ ✭ x ❀ θ ✵ ✮ ✰ ❤ θ � θ ✵ ❀ r θ ❢ ✭ x ❀ θ ✵ ✮ ✐ ✰ ♦ ✭ ❦ θ � θ ✵ ❦ ✷ ✮ ✿ ◮ Neural tangent model: the linear part of ❢ ❢ NT ✭ x ❀ β ❀ θ ✵ ✮ ❂ ❤ β ❀ r θ ❢ ✭ x ❀ θ ✵ ✮ ✐ ✿ [Jacot, Gabriel, Hongler, 2018] [Chizat, Bach, 2018b]

  15. Linear regression over random features ◮ NT model: the linear part of ❢ ❢ NT ✭ x ❀ β ❀ θ ✵ ✮ ❂ ❤ β ❀ ✣ ✭ x ✮ ✐ ❂ ❤ β ❀ r θ ❢ ✭ x ❀ θ ✵ ✮ ✐ ✿ ◮ (Random) feature map: ✣ ✭ ✁ ✮ ❂ r θ ❢ ✭ ✁ ❀ θ ✵ ✮ ✿ R ❞ ✦ R ◆ . ◮ Training dataset: ✭ ❳ ❀ ❨ ✮ ❂ ✭ x ✐ ❀ ② ✐ ✮ ✐ ✷ ❬ ♥ ❪ . ◮ Gradient flow dynamics: ❞ ❞ t β t ❂ � r β ❫ β ✵ ❂ 0 ✿ E ❬✭ ② � ❢ NT ✭ x ❀ β t ❀ θ ✵ ✮✮ ✷ ❪ ❀ ◮ Linear convergence: ☞ t ✦ ❫ β ❂ ✣ ✭ ❳ ✮ ② ❨ .

  16. Linear regression over random features ◮ NT model: the linear part of ❢ ❢ NT ✭ x ❀ β ❀ θ ✵ ✮ ❂ ❤ β ❀ ✣ ✭ x ✮ ✐ ❂ ❤ β ❀ r θ ❢ ✭ x ❀ θ ✵ ✮ ✐ ✿ ◮ (Random) feature map: ✣ ✭ ✁ ✮ ❂ r θ ❢ ✭ ✁ ❀ θ ✵ ✮ ✿ R ❞ ✦ R ◆ . ◮ Training dataset: ✭ ❳ ❀ ❨ ✮ ❂ ✭ x ✐ ❀ ② ✐ ✮ ✐ ✷ ❬ ♥ ❪ . ◮ Gradient flow dynamics: ❞ ❞ t β t ❂ � r β ❫ β ✵ ❂ 0 ✿ E ❬✭ ② � ❢ NT ✭ x ❀ β t ❀ θ ✵ ✮✮ ✷ ❪ ❀ ◮ Linear convergence: ☞ t ✦ ❫ β ❂ ✣ ✭ ❳ ✮ ② ❨ .

  17. Linear regression over random features ◮ NT model: the linear part of ❢ ❢ NT ✭ x ❀ β ❀ θ ✵ ✮ ❂ ❤ β ❀ ✣ ✭ x ✮ ✐ ❂ ❤ β ❀ r θ ❢ ✭ x ❀ θ ✵ ✮ ✐ ✿ ◮ (Random) feature map: ✣ ✭ ✁ ✮ ❂ r θ ❢ ✭ ✁ ❀ θ ✵ ✮ ✿ R ❞ ✦ R ◆ . ◮ Training dataset: ✭ ❳ ❀ ❨ ✮ ❂ ✭ x ✐ ❀ ② ✐ ✮ ✐ ✷ ❬ ♥ ❪ . ◮ Gradient flow dynamics: ❞ ❞ t β t ❂ � r β ❫ β ✵ ❂ 0 ✿ E ❬✭ ② � ❢ NT ✭ x ❀ β t ❀ θ ✵ ✮✮ ✷ ❪ ❀ ◮ Linear convergence: ☞ t ✦ ❫ β ❂ ✣ ✭ ❳ ✮ ② ❨ .

  18. Linear regression over random features ◮ NT model: the linear part of ❢ ❢ NT ✭ x ❀ β ❀ θ ✵ ✮ ❂ ❤ β ❀ ✣ ✭ x ✮ ✐ ❂ ❤ β ❀ r θ ❢ ✭ x ❀ θ ✵ ✮ ✐ ✿ ◮ (Random) feature map: ✣ ✭ ✁ ✮ ❂ r θ ❢ ✭ ✁ ❀ θ ✵ ✮ ✿ R ❞ ✦ R ◆ . ◮ Training dataset: ✭ ❳ ❀ ❨ ✮ ❂ ✭ x ✐ ❀ ② ✐ ✮ ✐ ✷ ❬ ♥ ❪ . ◮ Gradient flow dynamics: ❞ ❞ t β t ❂ � r β ❫ β ✵ ❂ 0 ✿ E ❬✭ ② � ❢ NT ✭ x ❀ β t ❀ θ ✵ ✮✮ ✷ ❪ ❀ ◮ Linear convergence: ☞ t ✦ ❫ β ❂ ✣ ✭ ❳ ✮ ② ❨ .

  19. Linear regression over random features ◮ NT model: the linear part of ❢ ❢ NT ✭ x ❀ β ❀ θ ✵ ✮ ❂ ❤ β ❀ ✣ ✭ x ✮ ✐ ❂ ❤ β ❀ r θ ❢ ✭ x ❀ θ ✵ ✮ ✐ ✿ ◮ (Random) feature map: ✣ ✭ ✁ ✮ ❂ r θ ❢ ✭ ✁ ❀ θ ✵ ✮ ✿ R ❞ ✦ R ◆ . ◮ Training dataset: ✭ ❳ ❀ ❨ ✮ ❂ ✭ x ✐ ❀ ② ✐ ✮ ✐ ✷ ❬ ♥ ❪ . ◮ Gradient flow dynamics: ❞ ❞ t β t ❂ � r β ❫ β ✵ ❂ 0 ✿ E ❬✭ ② � ❢ NT ✭ x ❀ β t ❀ θ ✵ ✮✮ ✷ ❪ ❀ ◮ Linear convergence: ☞ t ✦ ❫ β ❂ ✣ ✭ ❳ ✮ ② ❨ .

  20. Neural network ✙ Neural tangent Theorem [Jacot, Gabriel, Hongler, 2018] (Informal) Consider neural networks ❢ ◆ ✭ x ❀ θ ✮ with number of neurons ◆ , and consider ❞ ❞ t θ t ❂ � r θ ❫ θ ✵ ❂ θ ✵ ❀ E ❬✭ ② � ❢ ◆ ✭ x ❀ θ t ✮✮ ✷ ❪ ❀ ❞ ❞ t β t ❂ � r β ❫ β ✵ ❂ 0 ✿ E ❬✭ ② � ❢ ◆ NT ✭ x ❀ β t ❀ θ ✵ ✮✮ ✷ ❪ ❀ Under proper (random) initialization, we have a.s. ◆ ✦✶ ❥ ❢ ◆ ✭ x ❀ θ t ✮ � ❢ ◆ NT ✭ x ❀ β t ✮ ❥ ❂ ✵ ✿ ❧✐♠

  21. Optimization success Gradient flow of training loss of NN converges to global min ... ... with over-parameterization and proper initialization [Jacot, Gabriel, Hongler, 2018], [Du, Zhai, Poczos, Singh, 2018], [Du, Lee, Li, Wang, Zhai, 2018], [Allen-Zhu, Li, Song 2018], [Zou, Cao, Zhou, Gu, 2018], [Oymak, Soltanolkotabi, 2018] [Chizat, Bach, 2018b], ....

  22. Optimization success Gradient flow of training loss of NN converges to global min ... ... with over-parameterization and proper initialization [Jacot, Gabriel, Hongler, 2018], [Du, Zhai, Poczos, Singh, 2018], [Du, Lee, Li, Wang, Zhai, 2018], [Allen-Zhu, Li, Song 2018], [Zou, Cao, Zhou, Gu, 2018], [Oymak, Soltanolkotabi, 2018] [Chizat, Bach, 2018b], .... Does linearization fully explain the success of neural networks?

  23. Optimization success Gradient flow of training loss of NN converges to global min ... ... with over-parameterization and proper initialization [Jacot, Gabriel, Hongler, 2018], [Du, Zhai, Poczos, Singh, 2018], [Du, Lee, Li, Wang, Zhai, 2018], [Allen-Zhu, Li, Song 2018], [Zou, Cao, Zhou, Gu, 2018], [Oymak, Soltanolkotabi, 2018] [Chizat, Bach, 2018b], .... Does linearization fully explain the success of neural networks? Our answer is No

  24. Generalization Empirically, the generalization of NT models are not as good as NN Table: Cifar10 experiments Architecture Classification error CNN 4%- (1) CNTK 23% (2) CNTK 11% (3) Compositioal Kernel 10% (1) [Arora, Du, Hu, Li, Salakhutdinov, Wang, 2019] , (2) [Li, Wang, Yu, Du, Hu, Salakhutdinov, Arora, 2019] , (3) [Shankar, Fang, Guo, Fridovich-Keil, Schmidt, Ragan-Kelley, Recht, 2020] .

  25. Performance gap: NN versus NT

  26. Two-layers neural network ◆ ❳ ❢ ◆ ✭ x ❀ Θ ✮ ❂ ❛ ✐ ✛ ✭ ❤ w ✐ ❀ x ✐ ✮ ❀ Θ ❂ ✭ ❛ ✶ ❀ w ✶ ❀ ✿ ✿ ✿ ❀ ❛ ◆ ❀ w ◆ ✮ ✿ ✐ ❂✶ ◮ Input vector x ✷ R ❞ . ◮ Bottom layer weights w ✐ ✷ R ❞ , ✐ ❂ ✶ ❀ ✷ ❀ ✿ ✿ ✿ ❀ ◆ . ◮ Top layer weights ❛ ✐ ✷ R , ✐ ❂ ✶ ❀ ✷ ❀ ✿ ✿ ✿ ❀ ◆ .

Download Presentation
Download Policy: The content available on the website is offered to you 'AS IS' for your personal information and use only. It cannot be commercialized, licensed, or distributed on other websites without prior consent from the author. To download a presentation, simply click this link. If you encounter any difficulties during the download process, it's possible that the publisher has removed the file from their server.

Recommend

Neural Networks + Backpropagation Last Class Softmax Classifier Generalization /

Neural Networks + Backpropagation Last Class Softmax Classifier Generalization /

CS4501: Introduction to Computer Vision Neural Networks + Backpropagation Last Class Softmax Classifier Generalization / Overfitting Pytorch Todays Class Global Features The perceptron model Neural Networks

838 views • 34 slides
Learning From Data Lecture 22 Neural Networks and Overfitting Approximation vs. Generalization

Learning From Data Lecture 22 Neural Networks and Overfitting Approximation vs. Generalization

Learning From Data Lecture 22 Neural Networks and Overfitting Approximation vs. Generalization Regularization and Early Stopping Minimizing E in More Efficienty M. Magdon-Ismail CSCI 4100/6100 recap: Neural Networks and Fitting the Data

464 views • 15 slides
CSC413/2516 Lecture 7: Generalization & Recurrent Neural Networks Jimmy Ba Jimmy Ba

CSC413/2516 Lecture 7: Generalization & Recurrent Neural Networks Jimmy Ba Jimmy Ba

CSC413/2516 Lecture 7: Generalization & Recurrent Neural Networks Jimmy Ba Jimmy Ba CSC413/2516 Lecture 7: Generalization & Recurrent Neural Networks 1 / 57 Overview Weve focused so far on how to optimize neural nets how to get

971 views • 60 slides
Generalization Bounds of Stochastic Gradient Descent for Wide and Deep Neural Networks Yuan Cao

Generalization Bounds of Stochastic Gradient Descent for Wide and Deep Neural Networks Yuan Cao

Generalization Bounds of Stochastic Gradient Descent for Wide and Deep Neural Networks Yuan Cao and Quanquan Gu Computer Science Department 1 / 14 Learning Over-parameterized DNNs Empirical observation on extremely wide deep neural networks

631 views • 14 slides
Bayesian feedforward Neural networks Seung-Hoon Na Chonbuk National University Neural networks

Bayesian feedforward Neural networks Seung-Hoon Na Chonbuk National University Neural networks

Bayesian feedforward Neural networks Seung-Hoon Na Chonbuk National University Neural networks compared to GPs Neural networks: Nonlinear generalization of GLMs Here, defined by a logistic regression model applied to a logistic

357 views • 24 slides
Neural Networks for Machine Learning Lecture 9a Overview of ways to improve generalization

Neural Networks for Machine Learning Lecture 9a Overview of ways to improve generalization

Neural Networks for Machine Learning Lecture 9a Overview of ways to improve generalization Geoffrey Hinton Nitish Srivastava, Kevin Swersky Tijmen Tieleman Abdel-rahman Mohamed Reminder: Overfitting The training data contains information

1.17k views • 39 slides
Disentangling Trainability and Generalization In Deep Neural Networks Lechao Xiao, Je ff rey

Disentangling Trainability and Generalization In Deep Neural Networks Lechao Xiao, Je ff rey

Disentangling Trainability and Generalization In Deep Neural Networks Lechao Xiao, Je ff rey Pennington and Samuel S. Schoenholz Google Brain Team, Google Research Colab Tutorial Two Fundamental Theoretical Questions in Deep Learning

473 views • 15 slides
Linearized two-layers neural network in high dimensions Song Mei Stanford University May 26,

Linearized two-layers neural network in high dimensions Song Mei Stanford University May 26,

Linearized two-layers neural network in high dimensions Song Mei Stanford University May 26, 2019 Joint work with Andrea Montanari, Theodor Misiakiewicz, Behrooz Ghorbani Song Mei (Stanford University) Linearized two layers neural network

436 views • 39 slides
Lecture 4: Recurrent Neural Networks + Generalization Prof. Manolis Kellis Slides credit:

Lecture 4: Recurrent Neural Networks + Generalization Prof. Manolis Kellis Slides credit:

6.874, 6.802, 20.390, 20.490, HST.506 Computational Systems Biology Deep Learning in the Life Sciences Lecture 4: Recurrent Neural Networks + Generalization Prof. Manolis Kellis Slides credit: Geoffrey Hinton, Ian Goodfellow,

1.19k views • 86 slides
Neural Tangent Kernel Convergence and Generalization in Neural Networks Arthur Jacot Franck

Neural Tangent Kernel Convergence and Generalization in Neural Networks Arthur Jacot Franck

Neural Tangent Kernel Convergence and Generalization in Neural Networks Arthur Jacot Franck Gabriel Clment Hongler arthur.jacot@epfl.ch franck.gabriel@epfl.ch clement.hongler@epfl.ch What happens during training? One step of Gradient

248 views • 5 slides
Outline Evolution of neurocomputing Artificial neural networks Feed forward

Outline Evolution of neurocomputing Artificial neural networks Feed forward

Introduction to Neural Networks and Deep Learning Ling Guan References: S. Haykin, Neural Networks , 2 nd Edition, New Jersey: Prentice Hall, 1. 2004. C. M. Bishop, Neural Networks for Pattern Re cognition, New York: 2. Oxford University

451 views • 17 slides
Neural Networks 0. Logistics Spring 2019 1 Neural Networks are taking over! Neural networks

Neural Networks 0. Logistics Spring 2019 1 Neural Networks are taking over! Neural networks

Neural Networks 0. Logistics Spring 2019 1 Neural Networks are taking over! Neural networks have become one of the major thrust areas recently in various pattern recognition, prediction, and analysis problems In many problems they have

852 views • 33 slides
Neural Networks 1. Introduction Fall 2017 Neural Networks are taking over! Neural networks

Neural Networks 1. Introduction Fall 2017 Neural Networks are taking over! Neural networks

Neural Networks 1. Introduction Fall 2017 Neural Networks are taking over! Neural networks have become one of the major thrust areas recently in various pattern recognition, prediction, and analysis problems In many problems they have

1.17k views • 91 slides
CONVOLUTIONAL AND RECURRENT NEURAL NETWORKS Neural networks Fully connected networks

CONVOLUTIONAL AND RECURRENT NEURAL NETWORKS Neural networks Fully connected networks

CONVOLUTIONAL AND RECURRENT NEURAL NETWORKS Neural networks Fully connected networks Neuron Non-linearity Softmax layer DNN training Loss function and regularization SGD and backprop Learning rate Overfitting

1.8k views • 86 slides
Neural Networks 1. Introduction Spring 2019 1 Neural Networks are taking over! Neural

Neural Networks 1. Introduction Spring 2019 1 Neural Networks are taking over! Neural

Neural Networks 1. Introduction Spring 2019 1 Neural Networks are taking over! Neural networks have become one of the major thrust areas recently in various pattern recognition, prediction, and analysis problems In many problems they

1.57k views • 124 slides
Neural Networks 1. Introduction Spring 2020 1 Neural Networks are taking over! Neural

Neural Networks 1. Introduction Spring 2020 1 Neural Networks are taking over! Neural

Neural Networks 1. Introduction Spring 2020 1 Neural Networks are taking over! Neural networks have become one of the major thrust areas recently in various pattern recognition, prediction, and analysis problems In many problems they

1.63k views • 119 slides
On the Distribution of Random Staircase Tableaux Pawel Hitczenko & Amanda Parshall June 20,

On the Distribution of Random Staircase Tableaux Pawel Hitczenko & Amanda Parshall June 20,

On the Distribution of Random Staircase Tableaux Pawel Hitczenko & Amanda Parshall June 20, 2014 Pawel Hitczenko & Amanda Parshall On the Distribution of Random Staircase Tableaux Definition of Staircase Tableaux Pawel Hitczenko &

1.16k views • 52 slides
The Asymptotic Distribution of Symbols on Staircase Tableaux Diagonals Amanda Lohss September

The Asymptotic Distribution of Symbols on Staircase Tableaux Diagonals Amanda Lohss September

Definitions Connections/Motivation Previous Result Results The Asymptotic Distribution of Symbols on Staircase Tableaux Diagonals Amanda Lohss September 15, 2016 Amanda Lohss Purdue 2016 Definitions Connections/Motivation Previous Result

806 views • 58 slides
Staircase diagrams and the enumeration of smooth Schubert varieties Edward Richmond* and William

Staircase diagrams and the enumeration of smooth Schubert varieties Edward Richmond* and William

Staircase diagrams and the enumeration of smooth Schubert varieties Edward Richmond* and William Slofstra Oklahoma State University* University of Waterloo July 4, 2016 Richmond-Slofstra (OSU-Waterloo) Staircase diagrams July 4, 2016 1 / 16

320 views • 16 slides
Stair Caddy Carries items up to 50 lbs up and downstairs 2.009 Blue B Stair Caddy Design For

Stair Caddy Carries items up to 50 lbs up and downstairs 2.009 Blue B Stair Caddy Design For

Sketch Model Review Stair Caddy Carries items up to 50 lbs up and downstairs 2.009 Blue B Stair Caddy Design For the 36+ million senior citizens Existing Products AATA International SR 450 AATA International SR 1750 Comparison SR 450 SR

227 views • 10 slides
Enumeration of Permutation Classes by Inflation of Independent Sets of Graphs mile Nadeau

Enumeration of Permutation Classes by Inflation of Independent Sets of Graphs mile Nadeau

Enumeration of Permutation Classes by Inflation of Independent Sets of Graphs mile Nadeau (based on joint work with Christian Bean and Henning Ulfarsson) Reykjavik University Permutations Patterns 2019 Staircase encoding For any permutation

969 views • 78 slides
Workshop 1: Expressions NCTM Interac8ve Ins8tute, 2016 Introduc8ons Introduce yourself to

Workshop 1: Expressions NCTM Interac8ve Ins8tute, 2016 Introduc8ons Introduce yourself to

Workshop 1: Expressions NCTM Interac8ve Ins8tute, 2016 Introduc8ons Introduce yourself to others at your table: Name Where do you teach? What grades/classes do you teach? How long have you been teaching? Introduc8on Thats Me

532 views • 31 slides
Chip-Firing and A Devils Staircase Lionel Levine (MIT) FPSAC, July 21, 2009 Lionel Levine

Chip-Firing and A Devils Staircase Lionel Levine (MIT) FPSAC, July 21, 2009 Lionel Levine

Chip-Firing and A Devils Staircase Lionel Levine (MIT) FPSAC, July 21, 2009 Lionel Levine Chip-Firing and A Devils Staircase Talk Outline Mode locking in dynamical systems. Discrete: parallel chip-firing. Continuous: iteration

636 views • 31 slides
Enumerating Anchored Permutations with Bounded Gaps Maria Monks Gillespie, CSU Ken G. Monks,

Enumerating Anchored Permutations with Bounded Gaps Maria Monks Gillespie, CSU Ken G. Monks,

Enumerating Anchored Permutations with Bounded Gaps Maria Monks Gillespie, CSU Ken G. Monks, University of Scranton Ken M. Monks, Front Range Community College Rocky Mountain Algebraic Combinatorics Seminar Nov 15, 2019 Classical stair

741 views • 49 slides

More recommend