#### Filter Results:

- Full text PDF available (29)

#### Publication Year

2004

2018

- This year (7)
- Last 5 years (38)
- Last 10 years (39)

#### Publication Type

#### Co-author

#### Journals and Conferences

Learn More

Recent work has demonstrated that neural networks are vulnerable to adversarial examples, i.e., inputs that are almost indistinguishable from natural data and yet classified incorrectly by theâ€¦ (More)

We show the existence of a Locality-Sensitive Hashing (LSH) family for the angular distance that yields an approximate Near Neighbor Search algorithm with the asymptotically optimal running timeâ€¦ (More)

- Chinmay Hegde, Piotr Indyk, Ludwig Schmidt
- IJCAI
- 2015

We introduce a framework for sparsity structures defined via graphs. Our approach is flexible and generalizes several previously studied sparsity models. Moreover, we provide efficient projectionâ€¦ (More)

- Logan Engstrom, Dimitris Tsipras, Ludwig Schmidt, Aleksander Madry
- ArXiv
- 2017

Recent work has shown that neural networkâ€“based vision classifiers exhibit a significant vulnerability to misclassifications caused by imperceptible but adversarial perturbations of their inputs.â€¦ (More)

- Anna C. Gilbert, Piotr Indyk, Mark Iwen, Ludwig Schmidt
- IEEE Signal Processing Magazine
- 2014

The discrete Fourier transform (DFT) is a fundamental component of numerous computational techniques in signal processing and scientific computing. The most popular means of computing the DFT is theâ€¦ (More)

- Chinmay Hegde, Piotr Indyk, Ludwig Schmidt
- IEEE Transactions on Information Theory
- 2015

Compressive sensing (CS) states that a sparse signal can be recovered from a small number of linear measurements, and that this recovery can be performed efficiently in polynomial time. The frameworkâ€¦ (More)

- Chinmay Hegde, Piotr Indyk, Ludwig Schmidt
- SODA
- 2014

The goal of sparse recovery is to recover a k-sparse signal x âˆˆ R from (possibly noisy) linear measurements of the form y = Ax, where A âˆˆ RmÃ—n describes the measurement process. Standard results inâ€¦ (More)

- Chinmay Hegde, Piotr Indyk, Ludwig Schmidt
- Bulletin of the EATCS
- 2015

Sparse representations of signals (i.e., representations that have only few non-zero or large coefficients) have emerged as powerful tools in signal processing theory, algorithms, machine learningâ€¦ (More)

We design a new, fast algorithm for agnostically learning univariate probability distributions whose densities are well approximated by piecewise polynomial functions. Let f be the density functionâ€¦ (More)

- Ludwig Schmidt, Matthew Sharifi, Ignacio Lopez-Moreno
- 2014 IEEE International Conference on Acousticsâ€¦
- 2014

Speaker identification is one of the main tasks in speech processing. In addition to identification accuracy, large-scale applications of speaker identification give rise to another challenge: fastâ€¦ (More)