EE Student Information

The Department of Electrical Engineering supports Black Lives Matter. Read more.

• • • • •

EE Student Information, Spring Quarter through Academic Year 2020-2021: FAQs and Updated EE Course List.

Updates will be posted on this page, as well as emailed to the EE student mail list.

Please see Stanford University Health Alerts for course and travel updates.

As always, use your best judgement and consider your own and others' well-being at all times.

Information Systems Lab (ISL) Colloquium

ISL Colloquium presents "Extreme imaging with statistical signal processing"

Topic: 
Extreme imaging with statistical signal processing
Abstract / Description: 

Emerging technologies have given us an unprecedented ability to measure and manipulate light: We can now time-stamp individual photons and adaptively shape the phase profile of a laser beam. These capabilities stand to fundamentally change how we approach many imaging problems. However, using these capabilities effectively requires us to rethink how we process optical signals.

Statistical signal processing is a powerful lens through which to view imaging. It allows us to abstract complex physical problems into manageable representations and develop unconventional solutions.

In this talk I will briefly discuss how statistical signal processing can be used to solve four extreme imaging problems - problems for which conventional imaging techniques are doomed to fail: (1) Reconstructing a hidden object from measurements captured through the keyhole of a door. (2) Imaging through 27 attenuation lengths of fog. (3) Characterizing scattering media with intensity-only measurements. (4) Single-pixel compressive imaging without explicit priors nor ground-truth training data.


The Information Systems Laboratory Colloquium (ISLC)

is typically held in Packard 101 every Thursday at 4:30 pm during the academic year. Coffee and refreshments are served at 4pm in the second floor kitchen of Packard Bldg.

The Colloquium is organized by graduate students Joachim Neu, Tavor Baharav and Kabir Chandrasekher. To suggest speakers, please contact any of the students.

To receive email notifications of seminars you can join the ISL mailing list.

Date and Time: 
Thursday, November 21, 2019 - 4:30pm
Venue: 
Packard 101

IT-Forum and ISL Colloquium SPECIAL SEMINAR: "Towards an Average-case Complexity of High-dimensional Statistics"

Topic: 
Towards an Average-case Complexity of High-dimensional Statistics
Abstract / Description: 

The prototypical high-dimensional statistical estimation problem
entails finding a structured signal in noise. These problems have
traditionally been studied in isolation, with researchers aiming to
develop statistically and computationally efficient algorithms, as well
as to try to understand the fundamental limits governing the interplay
between statistical and computational cost. In this talk I will
describe a line of work that yields average-case reductions directly
between a number of central high-dimensional statistics problems,
relating two problems by transforming one into the other. It turns out
that several problems described by robust formulations can be addressed
by one set of techniques, and we will focus on these in the talk. In
this direction, we obtain the following average-case lower bounds based
on the planted clique conjecture: a statistical-computational gap in
robust sparse mean estimation, a detection-recovery gap in community
detection, and a universality principle for computational-statistical
gaps in sparse mixture estimation. In addition to showing strong
computational lower bounds tight against what is achievable by
efficient algorithms, the methodology gives insight into the common
features shared by different high-dimensional statistics problems with
similar computational behavior. Joint work with Matthew Brennan.


Special joint seminar:  IT-Forum and The Information Systems Laboratory Colloquium (ISLC)

Date and Time: 
Friday, November 15, 2019 - 1:15pm
Venue: 
Packard 202

ISL Colloquium presents "Spectral graph matching and regularized quadratic relaxations"

Topic: 
Spectral graph matching and regularized quadratic relaxations
Abstract / Description: 

Given two unlabeled, edge-correlated graphs on the same set of vertices, we study the "graph matching" problem of identifying the unknown mapping from vertices of the first graph to those of the second. This amounts to solving a computationally intractable quadratic assignment problem. We propose a new spectral method, which computes the eigendecomposition of the two graph adjacency matrices and returns a matching based on the pairwise alignments between all eigenvectors of the first graph with all eigenvectors of the second. Each alignment is inversely weighted by the distance between the corresponding eigenvalues. This spectral method can be equivalently viewed as solving a regularized quadratic programming relaxation of the quadratic assignment problem. We show that for a correlated Erdos-Renyi model, this method can return the exact matching with high probability if the two graphs differ by at most a 1/polylog(n) fraction of edges, both for dense graphs and for sparse graphs with at least polylog(n) average degree. Our analysis exploits local laws for the resolvents of sparse Wigner matrices. Based on joint work with Zhou Fan, Cheng Mao, Yihong Wu, all at Yale.


The Information Systems Laboratory Colloquium (ISLC)

is typically held in Packard 101 every Thursday at 4:30 pm during the academic year. Coffee and refreshments are served at 4pm in the second floor kitchen of Packard Bldg.

The Colloquium is organized by graduate students Joachim Neu, Tavor Baharav and Kabir Chandrasekher. To suggest speakers, please contact any of the students.

To receive email notifications of seminars you can join the ISL mailing list.

Date and Time: 
Thursday, November 14, 2019 - 4:30pm
Venue: 
Packard 101

ISL Colloquium Presents "Beyond Supervised Learning for Biomedical Imaging"

Topic: 
Beyond Supervised Learning for Biomedical Imaging
Abstract / Description: 

Today, many biomedical imaging tasks, such as 3D reconstruction, denoising, detection, registration, and segmentation, are solved with machine learning techniques. In this talk, I will present a flexible learning-based framework that has allowed us to derive efficient solutions for a variety of such problems, without relying on heavy supervision. I will primarily employ image registration as a concrete application and present the details of VoxelMorph, our unsupervised learning-based image registration tool. I will show empirical results obtained by co-registering thousands of brain MRI scans where VoxelMorph has yielded state-of-the-art accuracy with runtimes that are orders of magnitude faster than conventional tools. Finally, I will present some recent results where we used VoxelMorph to learn conditional deformable templates that can reveal population variation as a function of factors of interest, such as aging or genetics. Our code is freely available at https://github.com/voxelmorph/voxelmorph.


The Information Systems Laboratory Colloquium (ISLC)

is typically held in Packard 101 every Thursday at 4:30 pm during the academic year. Coffee and refreshments are served at 4pm in the second floor kitchen of Packard Bldg.

The Colloquium is organized by graduate students Joachim Neu, Tavor Baharav and Kabir Chandrasekher. To suggest speakers, please contact any of the students.

To receive email notifications of seminars you can join the ISL mailing list.

Date and Time: 
Thursday, November 7, 2019 - 4:30pm
Venue: 
Packard 101

ISL Colloquium presents Iterative Collaborative Filtering for Sparse Noisy Tensor Estimation

Topic: 
Iterative Collaborative Filtering for Sparse Noisy Tensor Estimation
Abstract / Description: 

We present a generalization of the collaborative filtering algorithm for the task of tensor estimation, i.e. estimating a low-rank 3-order n-by-n-by-n tensor from noisy observations of randomly chosen entries in the sparse regime. Not only does the algorithm have desirable computational properties, it also provably achieves sample complexity that (nearly) matches the conjectured lower bound on the sample complexity. Furthermore, our analysis results in high probability bounds on the infinity norm of the error, as opposed to the weaker MSE bounds achieved by previous approaches. Our proposed algorithm uses the matrix obtained from the ''flattened'' tensor to compute similarity with respect to a corresponding observation graph. The algorithm recovers the tensor with max entrywise error decaying to 0 with high probability as long as the entries are sampled uniformly at a density of Omega(n^{-3/2 + epsilon}) for any arbitrarily small epsilon > 0. This sample complexity threshold (nearly) matches a conjectured lower bound as well as the ''connectivity threshold'' of the corresponding observation graph used in our algorithm, providing a different angle to explain the conjectured lower bound.


The Information Systems Laboratory Colloquium (ISLC)

is typically held in Packard 101 every Thursday at 4:30 pm during the academic year. Coffee and refreshments are served at 4pm in the second floor kitchen of Packard Bldg.

The Colloquium is organized by graduate students Joachim Neu, Tavor Baharav and Kabir Chandrasekher. To suggest speakers, please contact any of the students.

To receive email notifications of seminars you can join the ISL mailing list.

Date and Time: 
Thursday, October 31, 2019 - 4:30pm
Venue: 
Packard 101

ISL Colloquium wpresents "Structure in high-dimensional non-parametric problems: Two modern vignettes"

Topic: 
Structure in high-dimensional non-parametric problems: Two modern vignettes
Abstract / Description: 

Non-parametric estimation problems in high dimensions see applications across scientific disciplines. However, they suffer from the curse of dimensionality: The number of samples required to achieve a prescribed error tolerance grows exponentially in the ambient dimension. It is thus of interest to impose natural structure in such problems to ensure both sample-efficiency and computational tractability. This talk will present two modern takes on classical problems in this space.

The first is the problem of fitting high dimensional convex functions from noisy observations, also known as convex regression. In order to avoid the curse of dimensionality, we study the problem of "max-affine" regression, in which the underlying convex function is equipped with additional structure and can be written as the point-wise maximum of a small number of affine functions. We analyze a well-known alternating minimization heuristic for this task, showing that it converges to the true model, at the optimal rate, under some random design assumptions.

The second vignette concerns the single-index model, which is a widely used semi-parametric model for non-linear dimensionality reduction. We describe a new, computationally efficient methodology for parameter estimation under this model that generalizes known heuristics for special cases, and achieves automatic adaptation to the noise level of the problem. Consequently, when the signal-to-noise to noise ratio in the model is high, we significantly reduce the bias in classical approaches in order to provide much sharper parameter estimates.

Throughout the talk, connections will be made to phase retrieval, which is a widely studied special case of both of these problems. The talk is based on joint work with Dean P. Foster, Avishek Ghosh, Adityanand Guntuboyina, Kannan Ramchandran, and Martin J. Wainwright.


The Information Systems Laboratory Colloquium (ISLC)

is typically held in Packard 101 every Thursday at 4:30 pm during the academic year. Coffee and refreshments are served at 4pm in the second floor kitchen of Packard Bldg.

The Colloquium is organized by graduate students Joachim Neu, Tavor Baharav and Kabir Chandrasekher. To suggest speakers, please contact any of the students.

To receive email notifications of seminars you can join the ISL mailing list.

Date and Time: 
Thursday, October 24, 2019 - 4:30pm
Venue: 
Packard 101

ISL Colloquium presents "Simple Near-Optimal Scheduling for the M/G/1"

Topic: 
Simple Near-Optimal Scheduling for the M/G/1
Abstract / Description: 

We consider the problem of preemptively scheduling jobs to minimize mean response time of an M/G/1 queue. When the scheduler knows each job's size, the shortest remaining processing time (SRPT) policy is optimal. Unfortunately, in many settings we do not have access to each job's size. Instead, we know only the job size distribution. In this setting, the Gittins policy is known to minimize mean response time, but its complex priority structure can be computationally intractable. A much simpler alternative to Gittins is the shortest expected remaining processing time (SERPT) policy. While SERPT is a natural extension of SRPT to unknown job sizes, it is unknown how close SERPT is to optimal.

We present a new variant of SERPT called monotonic SERPT (M-SERPT) which is as simple as SERPT but has provably near-optimal mean response time at all loads for any job size distribution. Specifically, we prove the mean response time ratio between M-SERPT and Gittins is at most 3 for load ρ ≤ 8/9 and at most 5 for any load. This makes M-SERPT the only scheduling policy known to be a constant-factor approximation of Gittins.

 


 

The Information Systems Laboratory Colloquium (ISLC)

is typically held in Packard 101 every Thursday at 4:30 pm during the academic year. Coffee and refreshments are served at 4pm in the second floor kitchen of Packard Bldg.

The Colloquium is organized by graduate students Joachim Neu, Tavor Baharav and Kabir Chandrasekher. To suggest speakers, please contact any of the students.

To receive email notifications of seminars you can join the ISL mailing list.

Date and Time: 
Thursday, October 17, 2019 - 4:30pm
Venue: 
Packard 101

ISL Colloquium presents "Algorithms for robust and heavy-tailed statistics -- theory and experiment"

Topic: 
Algorithms for robust and heavy-tailed statistics -- theory and experiment
Abstract / Description: 

Algorithms for statistics on corrupted or heavy-tailed data have seen a flurry activity in the last few years. (Indeed, even the last few months!) I will survey some recent developments, and then zoom in on joint work with Yihe Dong and Jerry Li in which we focus on translating the progress in polynomial-time algorithms into something practical. In particular, we obtain the first nearly-linear time algorithm for robust mean estimation in high dimensions, where the goal is to estimate the mean of a random vector from independent samples of which a constant fraction have been maliciously corrupted. Our algorithm is sufficiently practical that our implementation scales to thousands of dimensions and tens/hundreds of thousands of samples on laptop hardware; I will discuss some experimental validations of our theoretical results.

Based on "Quantum Entropy Scoring for Fast Robust Mean Estimation and Improved Outlier Detection," to appear in NeurIPS 2019. https://arxiv.org/pdf/1906.11366.pdf 


 

The Information Systems Laboratory Colloquium (ISLC)

is typically held in Packard 101 every Thursday at 4:30 pm during the academic year. Coffee and refreshments are served at 4pm in the second floor kitchen of Packard Bldg.

The Colloquium is organized by graduate students Joachim Neu, Tavor Baharav and Kabir Chandrasekher. To suggest speakers, please contact any of the students.

To receive email notifications of seminars you can join the ISL mailing list.

Date and Time: 
Thursday, October 10, 2019 - 4:30pm
Venue: 
Packard 101

ISL Colloquium presents "Denoising and Regularization via Exploiting the Structural Bias of Convolutional Generators"

Topic: 
Denoising and Regularization via Exploiting the Structural Bias of Convolutional Generators
Abstract / Description: 

Convolutional Neural Networks (CNNs) have emerged as highly successful tools for image generation, recovery, and restoration. This success is often attributed to large amounts of training data.
On the contrary, a number of recent experimental results suggest that a major contributing factor to this success is that convolutional networks impose strong prior assumptions about natural images. A surprising experiment that highlights this structural bias towards simple, natural images is that one can remove various kinds of noise and corruptions from a corrupted natural image by simply fitting (via gradient descent) a randomly initialized, over-parameterized convolutional generator to this single image. While this over-parameterized model can eventually fit the corrupted image perfectly, surprisingly after a few iterations of gradient descent one obtains the uncorrupted image, without using any training data. This intriguing phenomena has enabled state-of-the-art CNN-based denoising as well as regularization in linear inverse problems such as compressive sensing.
In this talk we take a step towards explaining this experimental phenomena by attributing it to particular architectural choices of convolutional networks. We then characterize the dynamics of fitting a two layer convolutional generator to a noisy signal and prove that early-stopped gradient descent denoises/regularizes. This results relies on showing that convolutional generators fit the structured part of an image significantly faster than the corrupted portion.

Based on joint work with Paul Hand and Mahdi Soltanolkotabi.

 


 

The Information Systems Laboratory Colloquium (ISLC)

is typically held in Packard 101 every Thursday at 4:30 pm during the academic year. Coffee and refreshments are served at 4pm in the second floor kitchen of Packard Bldg.

The Colloquium is organized by graduate students Joachim Neu, Tavor Baharav and Kabir Chandrasekher. To suggest speakers, please contact any of the students.

To receive email notifications of seminars you can join the ISL mailing list.

Date and Time: 
Thursday, October 3, 2019 - 4:30pm
Venue: 
Packard 101

ISL Colloquium presents " New Problems and Perspectives on Learning, Sampling, and Memory, in the Small Data Regime"

Topic: 
New Problems and Perspectives on Learning, Sampling, and Memory, in the Small Data Regime
Abstract / Description: 

I will discuss several new problems related to the general challenge of understanding what conclusions can be made, given a dataset that is relatively small in comparison to the complexity or dimensionality of the underlying distribution from which it is drawn. In the first setting we consider the problem of learning a population of Bernoulli (or multinomial) parameters. This is motivated by the ''federated learning" setting where we have data from a large number of heterogeneous individuals, who each supply a very modest amount of data, and ask the extent to which the number of data sources can compensate for the lack of data from each source. Second, I will introduce the problem of data "amplification". Given n independent draws from a distribution, D, to what extent is it possible to output a set of m > n datapoints that are indistinguishable from m i.i.d. draws from D? Curiously, we show that nontrivial amplification is often possible in the regime where n is too small to learn D to any nontrivial accuracy. We also discuss connections between this setting and the challenge of interpreting the behavior of GANs and other ML/AI systems. Finally (if there is time), I will also discuss memory/data tradeoffs for regression, with the punchline that any algorithm that uses a subquadratic amount of memory will require asymptotically more data than second-order methods to achieve comparable accuracy. This talk is based on four joint papers with various subsets of Weihao Kong, Brian Axelrod, Shivam Garg, Vatsal Sharan, Aaron Sidford, Sham Kakade, and Ramya Vinayak.

 


 

The Information Systems Laboratory Colloquium (ISLC)

is typically held in Packard 101 every Thursday at 4:30 pm during the academic year. Coffee and refreshments are served at 4pm in the second floor kitchen of Packard Bldg.

The Colloquium is organized by graduate students Joachim Neu, Tavor Baharav and Kabir Chandrasekher. To suggest speakers, please contact any of the students.

To receive email notifications of seminars you can join the ISL mailing list.

Date and Time: 
Thursday, September 26, 2019 - 4:30pm
Venue: 
Packard 101

Pages

Subscribe to RSS - Information Systems Lab (ISL) Colloquium