Conference Research Projects

Cleaning up toxic waste: Removing nefarious contributions to recommendation systems

Recommendation systems are becoming increasingly important, as evidenced by the popularity of the Netflix prize and the sophistication of various online shopping systems. With this increase in interest, a new problem of nefarious or false rankings that compromise a recommendation system’s integrity has surfaced. We consider such purposefully erroneous rankings to be a form of […]

Conference Research Projects

Invertible generative models for inverse problems: mitigating representation error and dataset bias

Trained generative models have shown remark-able performance as priors for inverse problems in imaging – for example, Generative Adversarial Network priors permit recovery of test images from 5-10x fewer measurements than sparsity priors. Unfortunately, these models may be unable to represent any particular image because of architectural choices, mode collapse, and bias in the training […]

Conference Research Projects

Compressive sampling of correlated signals

The recently developed theory of Compressive sensing (CS) has shown that sparse signals can be reconstructed from a much smaller number of measurements than their bandwidth suggests. In this paper we present a sampling scheme to acquire ensembles of correlated signals at a sub-Nyquist rate. The sampling architecture uses simple analog building blocks including analog […]

Conference Research Projects

Compressive Multiplexing of Correlated Signals

We propose two compressive multiplexers for the efficient sampling of ensembles of correlated signals. We show that we can acquire correlated ensembles, taking advantage of their (a priori-unknown) correlation structure, at a sub-Nyquist rate using simple modulation and filtering architectures. We recast the reconstruction of the ensemble as a low-rank matrix recovery problem from generalized […]

Conference Research Projects

Deep Ptych: Subsampled Fourier Ptychography Using Generative Priors

This paper proposes a novel framework to regularize the highly ill-posed and non-linear Fourier ptychography problem using generative models. We demonstrate experimentally that our proposed algorithm, Deep Ptych, outperforms the existing Fourier ptychography techniques, in terms of quality of reconstruction and robustness against noise, using far fewer samples. We further modify the proposed approach to […]

Conference Research Projects

Channel Protection Using Random Modulation

This paper shows that modulation protects a bandlimited signal against convolutive interference. A signal , bandlimited to BHz, is modulated (pointwise multiplied) with a known random sign sequence , alternating at a rate , and the resultant spread spectrum signal is convolved against an M-tap channel impulse response to yield the observed signal , where […]

wpChatIcon