lse-ml.github.io

Theory of ML Study Group

Meeting schedule

Michaelmans Term

The reading group sessions take place every second Tuesday, 15:00-16:30, Leverhulme library, Department of Statistics, 6th Floor, Columbia House.

#	Date	Topic	Discussion lead
1	2nd Oct, 2018	Deep Learning for Finance: Deep Portfolios, Heaton, Polson and Witte, 2016	Clifford Lam
2	16th Oct, 2018	No Spurious Local Minima in Nonconvex Low Rank Problems: A Unified Geometric Analysis, Ge, Jin and Zheng, ICML, 2017	Milan Vojnovic
3	30th Oct, 2018	A Latent Variable Model Approach to PMI-based Word Embeddings, Arora, Li, Liang, Ma, and Risteski, ACL 2016	Konstantin Kutzkov
4	13th Nov, 2018	Generative Adversarial Nets, GoodFellow et al, NIPS, 2014	Tianlin Xu
5	27th Nov, 2018	Hashing-Based-Estimators for Kernel Density in High Dimensions, Charikar and Siminelakis, FOCS, 2017	Zhenming Liu
6	11th Dec, 2018	Auto-encoding Variational Bayes, Kingma and Welling	Wonbong Jang

Lent Term (tentative schedule)

#	Date	Topic	Discussion lead
1	15th Jan, 2019	A General Theory for Large-Scale Curve Time Series via Functional Stability Measure, Guo and Qiao, arXiv 2018	Xinghao Qiao
2	29th Jan, 2019	Deep Learning: A Bayesian Perspective, Polson and Sokolov, Bayesian Analysis, 2017	Kostas Kalogeropoulos
3	12th Feb, 2019	Local Linear Forests, Friedberg, Tibshirani, Athey, & Wager arXiv, 2018	Filippo Pellegrino
4	26h Feb, 2019	Deep Reinforcement Learning: An Overview, Li, 2017; Human Level Control through Deep Reinforcement Learning, Mnih et al, Nature 518:529-533, 2015	Yining Chen
5	12th Mar, 2019	Global Convergence of Policy Gradient Methods for the Linear Quadratic Regulator, Fazel, Ge, Kakade and Mesbahi, ICML, 2018	Jialin Yi
6	26th Mar, 2019	Variational Inference: A Review for Statisticians, Blei, Kucukelbir and McAuliffe, 2016; Advances in Variational Inference, Zhang et al, 2017	Yirui Liu

Members

• Beatrice Acciaio
• Matteo Barigozzi
• Wicher Bergsma
• Luciano Campi
• Yining Chen
• Yunxiao Chen
• Qian Cheng
• Piotr Fryzlewicz
• Wonbong Jang
• Kostas Kalogeropoulos
• Kostas Kardaras
• Anica Kostic
• Konstantin Kutzkov
• Clifford Lam
• Yirui Liu
• Zhenming Liu
• Jose-Manuel Pedraza-Ramirez
• Filippo Pellegrino
• Xinghao Qiao
• Milan Vojnovic
• Weiguan Wang
• Yiliu Wang
• Tianlin Xu
• Qiwei Yao
• Jialin Yi
• Christine Yuen
• Kaifang Zhou

List of papers (in no particular order)

• Fazel, Ge, Kakade, and Mesbahi, Global Convergence of Policy Gradient Methods for the Linear Quadratic Regulator, ICML 2018 (JY)

• Friedberg, Tibshirani, Athey, & Wager, Local Linear Forests arXiv, 2018 (FP)

• Optimal transportation and generative models (BA)
  • Lei et al, A Geometric View of Optimal Transportation and Generative Model, 2017
  • Genevay, Peyre, and Cuturi, GAN and VAE from an Optimal Transport Point of View, 2017
  • Guo et al, Relaxed Wasserstein with Applications to GANs, 2018

• Kingma and Welling, Auto-encoding Variational Bayes, ICLR 2014 (WJ)

• Arora, Li, Liang, Ma, and Risteski, A Latent Variable Model Approach to PMI-based Word Embeddings, ACL 2016 (KK)
  • Levy and Goldberg, Neural Word Embedding as Implicit Matrix Factorization, NIPS 2014

• Sirignano and Spiliopoulos, Mean Field Analysis of Neural Networks, 2018 (LC)

• Ranganath and Blei, Correlated Random Measures, JASA, 2018 (XQ / YL)

• Qiao and Liu, Deep Hierarhical Dirichlet Process, in preparation, 2018 (XQ / YL)

• Colombo et al, Tomography of the London Underground: a Scalable Model for Origin-Destination Data, NIPS 2017 (KZ)

• Li, Deep Reinforcement Learning: An Overview, 2017; Mnih et al, Human Level Control through Deep Reinforcement Learning, Nature 518:529-533, 2015 (YC)

• Arora and Risteski, Provable Benefits of Representation Learning, 2017 (KK)

• Charikar and Siminelakis, Hashing-Based-Estimators for Kernel Density in High Dimensions, FOCS, 2017 (ZL)

• Lin, Tengmark and Rolinck, Why does Deep and Cheap Learning Work so Well?, 2016 (MB)

• Autoencoders, GANs … (TX)
  • GoodFellow et al, Generative Adversarial Nets, NIPS, 2014
  • Kingma and Welling, Auto-encoding Variational Bayes, ICLR 2014
  • Mohames and Lakshminarayanan, Learning Implicit Generative Models

• Polson and Sokolov, Deep Learning: A Bayesian Perspective, Bayesian Analysis, 2017 (KKal)

• Mahadevan et al, Systematic Topology Analysis and Generation Using Degree Correlations (QY)

• Heaton, Polson and Witte, Deep Learning for Finance: Deep Portfolios, SSRN, 2016 (CL)

• Muandet et al, Kernel and Mean Embedding of Distributions: A Review and Beyond, Foundations and Trends in Machine Learning, 2017 (WB)

• Ge, Jin and Zheng, No Spurious Local Minima in Nonconvex Low Rank Problems: A Unified Geometric Analysis, ICML, 2017 (MV)