Welcome to UCLA Data Mining Lab

Course Reading Groups

Fall 2023 Schedule: Physics-Informed Machine Learning (PIML)

Fall 2023 Schedule

Week	Topic	Presenter	Reading Materials	Slide Link	Youtube Link
1 - 2	Differentiable Physics with NNs	Fang Sun	PBDL Introduction (Review), PBDL Physical Loss, PBDL Differentiable Physics	Slides
3	Prof. Nitesh Chawla visits ScAI	Nitesh Chawla
4	Learning to Assess Disease and Health At Your Home	Guest Speaker: Yuzhe Yang
5	Differentiable Physics with NNs 2	Chenchen Ye	PBDL Differentiable Physics with NNs, Hamiltonian Neural Networks, Lagrangian Neural Networks	Slides
6	Improved Gradients	Anthony Cuturrufo
7	Unstructured Meshes and Meshless Methods	Arvind Vepa
8	Simulation	JeeHyun Hwang
9	Physical Discovery	Fred Xu

Winter 2023 Schedule: Diffusion Models and NeRF

Winter 2023 Schedule

Week	Topic	Presenter	Reading Materials	Slide Link	Youtube Link
1	Latent Diffusion (Stable-Diffusion) + Diffusion-LM	Patricia (Zhiping) Xiao		Slides
4	Latent Diffusion (Stable-Diffusion) + Diffusion-LM	Patricia (Zhiping) Xiao		Slides
5	Score-based Method	Xiao Luo		Drive
6	Image Editing	Yunsheng Bai
7	Faster Inference of Diffusion	Fred Xu
8	Planning via Diffusion	Xiusi Chen		Drive

Fall 2022 Schedule: Advance of Generative Model: Diffusion Model & NeRF

Fall 2022 Schedule

Week	Topic	Presenter	Reading Materials	Slide Link	Youtube Link
1	Diffusion Model Introduction	Fred Xu	Short Tutorial Blogpost by Lilian Weng Blog post by Yang Song DDPM (Denoising diffusion probabilistic models) DDIM (Denoising diffusion implicit models)	Slides
2	More on Diffusion Models	Ziniu Hu	Short Tutorial Blogpost by Lilian Weng Blog post by Yang Song DDPM (Denoising diffusion probabilistic models) DDIM (Denoising diffusion implicit models)
3	Diffusion model for text-to-image generation	Shichang Zhang	Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding Disco Diffusion	Slides
4	Imagen + Video Diffusion	Zongyue QIn	Hierarchical Text-Conditional Image Generation with CLIP Latents Video Diffusion Models
5	Palette + Composable Diffusion	Jeehyun Hwang	SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations Palette: Image-to-Image Diffusion Models Composable-Diffusion Compositional Visual Generation with Composable Diffusion Models
6	Torsional Diffusion + EDM + DIGRESS	Yanqiao Zhu	GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generation Torsional Diffusion for Molecular Conformer Generation
7	Classifier-free disfussion guidance	Song Jiang	Planning with Diffusion for Flexible Behavior Synthesis CLASSIFIER-FREE DIFFUSION GUIDANCE

Spring 2022 Schedule: Large Language Model

Spring 2022 Schedule

Week	Topic	Presenter	Reading Materials	Slide Link	Youtube Link
1	Introduction + Capabilities	Shichang	Introduction Capabilities On the Opportunities and Risks of Foundation Models (section 1, excluding 1.4).	Drive
2	Modeling + Training	Yewen	Modeling Training Hugging face blog Efficient Transformers: A Survey ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators
3	Modular architectures + Adaptation	Yunsheng	Selective Architectures Adaptaion Finetuned Language Models Are Zero-Shot Learners Multitask Prompted Training Enables Zero-Shot Task Generalization	Drive
4	Harms I + Harms II	Roshni	Harms-1 Harms-2 On the Dangers of Stochastic Parrots: Can Language Models Be Too Big? RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models	Drive
5	Data + Security and privacy	Derek	Data Security The Pile: An 800GB Dataset of Diverse Text for Language Modeling
6	Parallelism + Scaling laws	Zongyue	Parallelism Scaling Laws DeepSpeed: Extreme-scale model training for everyone
7	Visual+Language	Ziniu	OpenAI ClIP SimVLM: Simple Visual Language Model Pretraining with Weak Supervision
8	Legality + Environmental Impact	Junheng Hao	Legality Environment	Drive

Fall 2021 Schedule: Geometry

Fall 2021 Schedule

Week	Topic	Presenter	Reading Materials	Slide Link	Youtube Link
1	Introduction to Geometry	Song Jiang	Lecture 1 in Non-Euclidean Methods in Machine Leraning (NEM) Chapter in Shape Analysis (SA)	Drive
2	Curves	Shichang Zhang	Chapter 3 in SA Chapter 1 in DG	Drive
3	Surfaces and Manifolds	Zongyue Qin	Chapter 4 in SA Chapter 2 in DG	Drive
4	Curvature	Yunsheng Bai	Chapter 5 in SA Chapter 3 in DG
5	Geodesics Distances	Ziniu Hu	Chapter 6 in SA Chapter 4 in DG
6	Optimization on Riemannian manifolds	Arjun Subramonian	Lec 5 in NEM
7	Inverse Distance Problems	Fred Xu	Chapter 7 in SA
8	Algorithms on Riemannian manifolds	Kewei Cheng	Chapter 6 in NEM Chapter 10 in NEM
9	Probability on Riemannian manifolds & Sampling	Derek Xu	Chapter 8 in NEM
10	Riemannian Bayesian Inference	Zijie Huang	Chapter 9 in NEM
11	Matrix Manifolds and Applications in Computer Vision	Roshni Iyer	Chapter 7 in NEM	Drive
12	From Manifolds to Graphs: Laplacian	Zhiping(Patricia) Xiao	Chapter 9 in SA	File

Winter 2021 Schedule: Graphical Model

Winter 2021 Schedule

Week	Topic	Presenter	Reading Materials	Slide Link	Youtube Link
1	Introduction to GM + Undirected GMs	Arjun Subramonian	Slide 1 from CMU Slide 2 from CMU
2	Directed GMs + Exact Inference	Shirley Chen
3	Parameter Estimation + HMM and CRF	Derek Xu
4	Variational Inference	Yewen Wang		Drive
5	Sampling	Fred Xu		Drive
6	Deep Generative Models	Zhiping(Patricia) Xiao	File
7	Text Generation + Structure Learning	Ziniu Hu
8	Causality	Song Jiang
9	Reinforcement Learning as Inference	Roshni Iyer
10	Gaussian Process + Determinant Point Process	Shichang Zhang		Drive
11	Spectral Graphical Models + Large-scale Algorithms and Systems	Zijie Huang		Drive
12	Meta-Learning + Robust Machine Learning	Yunsheng Bai	Chapter 9 in SA	File

Fall 2020 Schedule: Spectral Graph Theory & Applications

Fall 2020 Schedule

Week	Topic	Presenter	Reading Materials	Slide Link	Youtube Link
1	The Laplacian Matrix and Spectral Graph Drawing. Courant-Fischer.	Zhiping Xiao	Chapter 1-3 Textbook One Textbook Tow 2.4	Slide
2	The Adjacency Matrix, interlacing, and Perron-Frobenius. Eigenvalue comparison theorems.	Yewen Wang	Chapter 4-5 Textbook One	Slide
3	The Zoo of graphs. Bounding eigenvalues by test vectors. Eigenvalues of random graphs	Shirley Chen	Textbook One Chapter 6 & 8	Slide
4	Eigenvalues and Graph Structure: cuts, partitions, and coloring.	Kewei Cheng	Textbook One Chapter 19, 20 Textbook Two Chapter 5	Slide
5	Random Walk	Zijie Huang	Textbook One Chapter 19, 20 Textbook Two Chapter 5	Slide
6	Graph Sparsification	Arjun Subramonian	Textbook One Chapter 32s Textbook Two Chapter 6	Slide
7	Graph Clustering	Ziniu Hu	Textbook One Chapter 22 Textbook Two Chapter 4	Slide