Alert button
Picture for John Wright

John Wright

Alert button

Department of Electrical Engineering, Columbia University Data Science Institute

TpopT: Efficient Trainable Template Optimization on Low-Dimensional Manifolds

Oct 16, 2023
Jingkai Yan, Shiyu Wang, Xinyu Rain Wei, Jimmy Wang, Zsuzsanna Márka, Szabolcs Márka, John Wright

Viaarxiv icon

Boosting the Efficiency of Parametric Detection with Hierarchical Neural Networks

Jul 23, 2022
Jingkai Yan, Robert Colgan, John Wright, Zsuzsa Márka, Imre Bartos, Szabolcs Márka

Figure 1 for Boosting the Efficiency of Parametric Detection with Hierarchical Neural Networks
Figure 2 for Boosting the Efficiency of Parametric Detection with Hierarchical Neural Networks
Figure 3 for Boosting the Efficiency of Parametric Detection with Hierarchical Neural Networks
Figure 4 for Boosting the Efficiency of Parametric Detection with Hierarchical Neural Networks
Viaarxiv icon

Resource-Efficient Invariant Networks: Exponential Gains by Unrolled Optimization

Mar 09, 2022
Sam Buchanan, Jingkai Yan, Ellie Haber, John Wright

Figure 1 for Resource-Efficient Invariant Networks: Exponential Gains by Unrolled Optimization
Figure 2 for Resource-Efficient Invariant Networks: Exponential Gains by Unrolled Optimization
Figure 3 for Resource-Efficient Invariant Networks: Exponential Gains by Unrolled Optimization
Figure 4 for Resource-Efficient Invariant Networks: Exponential Gains by Unrolled Optimization
Viaarxiv icon

Principal Component Pursuit for Pattern Identification in Environmental Mixtures

Oct 29, 2021
Elizabeth A. Gibson, Junhui Zhang, Jingkai Yan, Lawrence Chillrud, Jaime Benavides, Yanelli Nunez, Julie B. Herbstman, Jeff Goldsmith, John Wright, Marianthi-Anna Kioumourtzoglou

Figure 1 for Principal Component Pursuit for Pattern Identification in Environmental Mixtures
Figure 2 for Principal Component Pursuit for Pattern Identification in Environmental Mixtures
Figure 3 for Principal Component Pursuit for Pattern Identification in Environmental Mixtures
Figure 4 for Principal Component Pursuit for Pattern Identification in Environmental Mixtures
Viaarxiv icon

Deep Networks Provably Classify Data on Curves

Jul 29, 2021
Tingran Wang, Sam Buchanan, Dar Gilboa, John Wright

Viaarxiv icon

Square Root Principal Component Pursuit: Tuning-Free Noisy Robust Matrix Recovery

Jun 17, 2021
Junhui Zhang, Jingkai Yan, John Wright

Figure 1 for Square Root Principal Component Pursuit: Tuning-Free Noisy Robust Matrix Recovery
Figure 2 for Square Root Principal Component Pursuit: Tuning-Free Noisy Robust Matrix Recovery
Figure 3 for Square Root Principal Component Pursuit: Tuning-Free Noisy Robust Matrix Recovery
Figure 4 for Square Root Principal Component Pursuit: Tuning-Free Noisy Robust Matrix Recovery
Viaarxiv icon

ReduNet: A White-box Deep Network from the Principle of Maximizing Rate Reduction

Jun 10, 2021
Kwan Ho Ryan Chan, Yaodong Yu, Chong You, Haozhi Qi, John Wright, Yi Ma

Figure 1 for ReduNet: A White-box Deep Network from the Principle of Maximizing Rate Reduction
Figure 2 for ReduNet: A White-box Deep Network from the Principle of Maximizing Rate Reduction
Figure 3 for ReduNet: A White-box Deep Network from the Principle of Maximizing Rate Reduction
Figure 4 for ReduNet: A White-box Deep Network from the Principle of Maximizing Rate Reduction
Viaarxiv icon

Generalized Approach to Matched Filtering using Neural Networks

Apr 08, 2021
Jingkai Yan, Mariam Avagyan, Robert E. Colgan, Doğa Veske, Imre Bartos, John Wright, Zsuzsa Márka, Szabolcs Márka

Figure 1 for Generalized Approach to Matched Filtering using Neural Networks
Figure 2 for Generalized Approach to Matched Filtering using Neural Networks
Figure 3 for Generalized Approach to Matched Filtering using Neural Networks
Figure 4 for Generalized Approach to Matched Filtering using Neural Networks
Viaarxiv icon

Deep Networks from the Principle of Rate Reduction

Oct 27, 2020
Kwan Ho Ryan Chan, Yaodong Yu, Chong You, Haozhi Qi, John Wright, Yi Ma

Figure 1 for Deep Networks from the Principle of Rate Reduction
Figure 2 for Deep Networks from the Principle of Rate Reduction
Figure 3 for Deep Networks from the Principle of Rate Reduction
Figure 4 for Deep Networks from the Principle of Rate Reduction
Viaarxiv icon