Please note that ISTA Research Explorer no longer supports Internet Explorer versions 8 or 9 (or earlier).
We recommend upgrading to the latest Internet Explorer, Google Chrome, or Firefox.
10 Publications
2021 | Conference Paper | IST-REx-ID: 11453 | 
Braun, Lukas, and Tim P Vogels. “Online Learning of Neural Computations from Sparse Temporal Feedback.” In Advances in Neural Information Processing Systems - 35th Conference on Neural Information Processing Systems, 20:16437–50. Neural Information Processing Systems Foundation, 2021.
[Published Version]
View
| Download Published Version (ext.)
2021 | Conference Paper | IST-REx-ID: 11452 |
Alimisis, Foivos, Peter Davies, Bart Vandereycken, and Dan-Adrian Alistarh. “Distributed Principal Component Analysis with Limited Communication.” In Advances in Neural Information Processing Systems - 35th Conference on Neural Information Processing Systems, 4:2823–34. Neural Information Processing Systems Foundation, 2021.
[Published Version]
View
| Download Published Version (ext.)
| arXiv
2021 | Conference Paper | IST-REx-ID: 11463 |
Frantar, Elias, Eldar Kurtic, and Dan-Adrian Alistarh. “M-FAC: Efficient Matrix-Free Approximations of Second-Order Information.” In 35th Conference on Neural Information Processing Systems, 34:14873–86. Curran Associates, 2021.
[Published Version]
View
| Download Published Version (ext.)
| arXiv
2021 | Conference Paper | IST-REx-ID: 11464 |
Alistarh, Dan-Adrian, and Janne Korhonen. “Towards Tight Communication Lower Bounds for Distributed Optimisation.” In 35th Conference on Neural Information Processing Systems, 34:7254–66. Curran Associates, 2021.
[Published Version]
View
| Download Published Version (ext.)
| arXiv
2021 | Conference Paper | IST-REx-ID: 11458 |
Peste, Elena-Alexandra, Eugenia B Iofinova, Adrian Vladu, and Dan-Adrian Alistarh. “AC/DC: Alternating Compressed/DeCompressed Training of Deep Neural Networks.” In 35th Conference on Neural Information Processing Systems, 34:8557–70. Curran Associates, 2021.
[Published Version]
View
| Files available
| Download Published Version (ext.)
| arXiv
2021 | Conference Paper | IST-REx-ID: 14182 |
Träuble, Frederik, Julius von Kügelgen, Matthäus Kleindessner, Francesco Locatello, Bernhard Schölkopf, and Peter Gehler. “Backward-Compatible Prediction Updates: A Probabilistic Approach.” In 35th Conference on Neural Information Processing Systems, 34:116–28, 2021.
[Preprint]
View
| Download Preprint (ext.)
| arXiv
2021 | Conference Paper | IST-REx-ID: 14179 |
Kügelgen, Julius von, Yash Sharma, Luigi Gresele, Wieland Brendel, Bernhard Schölkopf, Michel Besserve, and Francesco Locatello. “Self-Supervised Learning with Data Augmentations Provably Isolates Content from Style.” In Advances in Neural Information Processing Systems, 34:16451–67, 2021.
[Preprint]
View
| Download Preprint (ext.)
| arXiv
2021 | Conference Paper | IST-REx-ID: 14180 |
Rahaman, Nasim, Muhammad Waleed Gondal, Shruti Joshi, Peter Gehler, Yoshua Bengio, Francesco Locatello, and Bernhard Schölkopf. “Dynamic Inference with Neural Interpreters.” In Advances in Neural Information Processing Systems, 34:10985–98, 2021.
[Preprint]
View
| Download Preprint (ext.)
| arXiv
2021 | Conference Paper | IST-REx-ID: 10593 |
Mondelli, Marco, and Ramji Venkataramanan. “PCA Initialization for Approximate Message Passing in Rotationally Invariant Models.” In 35th Conference on Neural Information Processing Systems, 35:29616–29. Neural Information Processing Systems Foundation, 2021.
[Preprint]
View
| Download Preprint (ext.)
| arXiv
2021 | Conference Paper | IST-REx-ID: 10594 |
Nguyen, Quynh, Pierre Bréchet, and Marco Mondelli. “When Are Solutions Connected in Deep Networks?” In 35th Conference on Neural Information Processing Systems, Vol. 35. Neural Information Processing Systems Foundation, 2021.
[Preprint]
View
| Download Preprint (ext.)
| arXiv