`

Timezone: »

 
Poster
Differentiable Spline Approximations
Minsu Cho · Aditya Balu · Ameya Joshi · Anjana Deva Prasad · Biswajit Khara · Soumik Sarkar · Baskar Ganapathysubramanian · Adarsh Krishnamurthy · Chinmay Hegde

Tue Dec 07 04:30 PM -- 06:00 PM (PST) @ None #None

The paradigm of differentiable programming has significantly enhanced the scope of machine learning via the judicious use of gradient-based optimization. However, standard differentiable programming methods (such as autodiff) typically require that the machine learning models be differentiable, limiting their applicability. Our goal in this paper is to use a new, principled approach to extend gradient-based optimization to functions well modeled by splines, which encompass a large family of piecewise polynomial models. We derive the form of the (weak) Jacobian of such functions and show that it exhibits a block-sparse structure that can be computed implicitly and efficiently. Overall, we show that leveraging this redesigned Jacobian in the form of a differentiable "layer'' in predictive models leads to improved performance in diverse applications such as image segmentation, 3D point cloud reconstruction, and finite element analysis. We also open-source the code at \url{https://github.com/idealab-isu/DSA}.

Author Information

Minsu Cho (New York University)
Aditya Balu (Iowa State University)
Ameya Joshi (Iowa State University)
Anjana Deva Prasad (Iowa State University)
Biswajit Khara (Iowa State University)
Soumik Sarkar (United Technologies Research Center)
Baskar Ganapathysubramanian (Iowa State University)
Adarsh Krishnamurthy (Iowa State University)
Chinmay Hegde (New York University)

More from the Same Authors

  • 2020 : Session B, Poster 30: Differentiable Programming For Piecewise Polynomial Functions »
    Minsu Cho
  • 2021 : A Graph Policy Network Approach for Volt-Var Control in Power Distribution Systems »
    Xian Yeow Lee · Soumik Sarkar
  • 2021 : Distributed Deep Learning for Persistent Monitoring of agricultural Fields »
    Yasaman Esfandiari · Koushik Nagasubramanian · Fateme Fotouhi · Patrick Schnable · Baskar Ganapathysubramanian · Soumik Sarkar
  • 2021 Poster: Implicit Sparse Regularization: The Impact of Depth and Early Stopping »
    Jiangyuan Li · Thanh Nguyen · Chinmay Hegde · Raymond K. W. Wong
  • 2020 : Poster Session B »
    Ravi Addanki · Andreea Deac · Yujia Xie · Francesco Landolfi · Antoine Prouvost · Claudius Gros · Renzo Massobrio · Abhishek Cauligi · Simon Alford · Hanjun Dai · Alberto Franzin · Nitish Kumar Panigrahy · Brandon Kates · Iddo Drori · Taoan Huang · Zhou Zhou · Marin Vlastelica · Anselm Paulus · Aaron Zweig · Minsu Cho · Haiyan Yin · Michal Lisicki · Nan Jiang · Haoran Sun
  • 2019 : Coffee + Posters »
    Ben Caine · Ren Wang · Nazmus Sakib · Nana Otawara · Meha Kaushik · elmira amirloo · Nemanja Djuric · Johanna Rock · Tanmay Agarwal · Angelos Filos · Panagiotis Tigkas · Donsuk Lee · Wootae Jeon · Nikita Jaipuria · Pin Wang · Jinxin Zhao · Liangjun Zhang · Ashutosh Singh · Ershad Banijamali · Mohsen Rohani · Aman Sinha · Ameya Joshi · Ching-Yao Chan · Mohammed Abdou Abdou · Changhao Chen · Jong-Chan Kim · eslam mohamed · Matt OKelly · Nirvan Singhania · Hiroshi Tsukahara · Atsushi Keyaki · Praveen Palanisamy · Justin Norden · Micol Marchetti-Bowick · Yiming Gu · Hitesh Arora · Shuby Deshpande · Jeff Schneider · Shangling Jui · Vaneet Aggarwal · Tryambak Gangopadhyay · Qiaojing Yan
  • 2019 : Poster Session »
    Eduard Gorbunov · Alexandre d'Aspremont · Lingxiao Wang · Liwei Wang · Boris Ginsburg · Alessio Quaglino · Camille Castera · Saurabh Adya · Diego Granziol · Rudrajit Das · Raghu Bollapragada · Fabian Pedregosa · Martin Takac · Majid Jahani · Sai Praneeth Karimireddy · Hilal Asi · Balint Daroczy · Leonard Adolphs · Aditya Rawal · Nicolas Brandt · Minhan Li · Giuseppe Ughi · Orlando Romero · Ivan Skorokhodov · Damien Scieur · Kiwook Bae · Konstantin Mishchenko · Rohan Anil · Vatsal Sharan · Aditya Balu · Chao Chen · Zhewei Yao · Tolga Ergen · Paul Grigas · Chris Junchi Li · Jimmy Ba · Stephen J Roberts · Sharan Vaswani · Armin Eftekhari · Chhavi Sharma
  • 2019 Poster: Algorithmic Guarantees for Inverse Imaging with Untrained Network Priors »
    Gauri Jagatap · Chinmay Hegde
  • 2018 : Contributed Work »
    Thaer Moustafa Dieb · Aditya Balu · Amir H. Khasahmadi · Viraj Shah · Boris Knyazev · Payel Das · Garrett Goh · Georgy Derevyanko · Gianni De Fabritiis · Reiko Hagawa · John Ingraham · David Belanger · Jialin Song · Kim Nicoli · Miha Skalic · Michelle Wu · Niklas Gebauer · Peter Bjørn Jørgensen · Ryan-Rhys Griffiths · Shengchao Liu · Sheshera Mysore · Hai Leong Chieu · Philippe Schwaller · Bart Olsthoorn · Bianca-Cristina Cristescu · Wei-Cheng Tseng · Seongok Ryu · Iddo Drori · Kevin Yang · Soumya Sanyal · Zois Boukouvalas · Rishi Bedi · Arindam Paul · Sam Ghosal · Daniil Bash · Clyde Fare · Zekun Ren · Ali Oskooei · Minn Xuan Wong · Paul Sinz · Théophile Gaudin · Wengong Jin · Paul Leu
  • 2017 Poster: Collaborative Deep Learning in Fixed Topology Networks »
    Zhanhong Jiang · Aditya Balu · Chinmay Hegde · Soumik Sarkar