Fall 2018 – Lecture series by Dr Chinmay Hegde and Dr Soumik Sarkar on Robustifying ML. Find the course plan here: Robustifying ML
(Note: Lectures 4 and 5 have been interchanged).
You can also find the lecture material in the Fall 2018 Talks tab.
We’re a group of graduate students from Iowa State University, with underlying interests in solving some cool data science problems.
We meet weekly on Fridays, from 12:00 pm to 1:00 pm at
Coover, 3043, Black 2004 (this week onward) to discuss varied problems in the intersection of our research areas (check the Research tab for more info). Occasionally, we enjoy active brainstorming sessions over cups of medium roast coffee.
You can find all material related to our seminars, including slides and references in the List of Talks tab.
Reblogging an insightful blog post on CLT and WLLN by one of our members!
Attend the #NVDLI #deeplearning workshop hosted by NVIDIA and Department of Mechanical Engineering, Iowa State University on November 3rd, 2018 from 8AM to 5PM. Register now!
The fourth session in the Robustifying ML series was conducted by Dr. Sarkar at 12pm in Black 2004. The lecture notes can be found here: Defenses.
The third lecture in the Robustifying ML series was conducted by Dr. Sarkar in Black 2004, on the 7th of September, 2018. The slides for the same can be found here: Slides: Attacks on RL.
The second session for this lecture series was conducted in Black Engineering 2004, at 12pm on August 31. Lecture notes for the same can be found below:
The first lecture in this series was conducted in Coover 3043 on the 24th of August by Dr. Chinmay Hegde.
You can find the notes on the topics covered, here:
This week, Viraj will be presenting the paper ” Solving Linear Inverse Problems Using GAN Priors: An Algorithm with Provable Guarantees” available at: https://arxiv.org/abs/1802.08406
In recent works, both sparsity-based methods as well as learning-based methods have proven to be successful in solving several challenging linear inverse problems. However, sparsity priors for natural signals and images suffer from poor discriminative capability, while learning-based methods seldom provide concrete theoretical guarantees. In this work, we advocate the idea of replacing hand-crafted priors, such as sparsity, with a Generative Adversarial Network (GAN) to solve linear inverse problems such as compressive sensing. In particular, we propose a projected gradient descent (PGD) algorithm for effective use of GAN priors for linear inverse problems, and also provide theoretical guarantees on the rate of convergence of this algorithm. Moreover, we show empirically that our algorithm demonstrates superior performance over an existing method of leveraging GANs for compressive sensing.
Time: 12.10 – 1.00 PM, Friday, April 06.
For these two weeks, Praneeth will be presenting the paper “Robust Subspace Clustering” which is available at “https://arxiv.org/abs/1301.
This chalk on blackboard talk will mostly focus on the algorithm and an overview of the theoretical results presented in the paper.
This week’s speaker for the DSRG seminar series is Rahul Singh. He will talk about Graph Convolutional Neural Networks. The abstract and references are as follows.
– In social networks, the characteristics of users can be modeled as signals on the vertices of the social graph
– In sensor networks, the sensor reading are modeled as time-dependent signals on the vertices
– In genetics, gene expression data are modeled as signals defined on the regulatory network
The non-Euclidean nature of such data implies that there are no such familiar properties as common system of coordinates, vector space structure, or shift-invariance. Consequently, basic operations like convolution and shifting that are taken for granted in the Euclidean case are even not well defined on non-Euclidean domains.
The talk will be about the recent efforts made towards the generalization of CNNs from low-dimensional regular grids to high-dimensional irregular domains such as graphs.”
Michaël Defferrard et al., “Convolutional neural networks on graphs with fast localized spectral filtering.” In Advances in Neural Information Processing Systems, pp. 3844-3852. 2016.
Thomas Kipf and Max Welling, ” Semi-supervised classification with graph convolutional networks.” In Proceedings of International Conference on Learning Representations, 2017.
Michael Bronstein et al., “Geometric deep learning: going beyond euclidean data.” IEEE Signal Processing Magazine 34.4 (2017): 18-42.