See also my Google Scholar.

*Denotes first author or co-first author paper.

  1. *B. Hanin, D. Rolnick, Complexity of linear regions in deep networks, preprint arXiv:1901.09021, 2019.
  2. A. Benjamin, D. Rolnick, K. Kording, Measuring and regularizing networks in function space, International Conference on Learning Representations (ICLR) 2019.
  3. *D. Rolnick, A. Ahuja, J. Schwarz, T.P. Lillicrap, G. Wayne, Experience replay for continual learning, preprint arXiv:1811.11682, 2018.
  4. Y. Meirovitch, L. Mi, H. Saribekyan, A. Matveev, D. Rolnick, C. Wierzynski, N. Shavit, Cross-classification clustering: An efficient multi-object tracking technique for 3-D instance segmentation in connectomics, preprint arXiv:1812.01157, 2018.
  5. *B. Hanin, D. Rolnick, How to start training: The effect of initialization and architecture, Conference on Neural Information Processing Systems (NIPS) 2018.
  6. *D. Rolnick, M.Tegmark, The power of deeper networks for expressing natural functions, International Conference on Learning Representations (ICLR) 2018.
  7. *R. Farhoodi, D. Rolnick, K. Kording, Neuron dendrograms uncover asymmetrical motifs, Computational and Systems Neuroscience (Cosyne) 2018.
  8. *G. Spencer, D. Rolnick, On the robust hardness of Gröbner basis computation, Journal of Pure and Applied Algebra 223(5):2080-2100, 2019.
  9. *D. Rolnick, A. Veit, S. Belongie, N. Shavit, Deep learning is robust to massive label noise, preprint arXiv:1705.10694, 2017.
  10. *D. Rolnick, Y. Meirovitch, T. Parag, H. Pfister, V. Jain, J.W. Lichtman, E.S. Boyden, N.~Shavit, Morphological error detection in 3D segmentations, preprint arXiv:1705.10882, 2017.
  11. H. Lin, M. Tegmark, D. Rolnick, Why does deep and cheap learning work so well?, Journal of Statistical Physics 168(6):1223-1247, 2017.
  12. *D. Rolnick, J. Bernstein, I. Dasgupta, H. Sompolinsky, Markov transitions between attractor states in a recurrent neural network, Computational and Systems Neuroscience (Cosyne) 2017.
  13. *D. Rolnick, P. Soberón, Quantitative (p,q)-theorems in combinatorial geometry, Discrete Mathematics 340(10):2516-2527, 2017.
  14. *J.A. De Loera, R.N. La Haye, D. Rolnick, and P. Soberón, Quantitative Tverberg theorems over lattices and other discrete sets, Discrete \& Computational Geometry 58(2):435-448, 2017.
  15. *J.A. De Loera, R.N. La Haye, D. Rolnick, and P. Soberón, Quantitative combinatorial geometry for continuous parameters, Discrete & Computational Geometry 57(2):318-334, 2017.
  16. *D. Rolnick, On the classification of Stanley sequences, European Journal of Combinatorics 59:51-70, 2017.
  17. Y. Meirovitch, A. Matveev, H. Saribekyan, D. Budden, D. Rolnick, G. Odor, S. Knowles-Barley, T. Jones, H. Pfister, J.W. Lichtman, N. Shavit, A multi-pass approach to large-scale connectomics, preprint arXiv:1612.02120, 2016.
  18. *D. Rolnick, K. Aydin, S. Kamali, V. Mirrokni, A. Najmi, GeoCUTS: Geographic clustering using transit statistics, preprint arXiv:1611.03780, 2016.
  19. *D. Rolnick, P. Soberón, Algorithmic aspects of Tverberg’s theorem, preprint arXiv:1601.03083, 2016.
  20. *R.A. Moy and D. Rolnick, Novel structures in Stanley sequences, Discrete Mathematics 339(2):689-698, 2016.
  21. *N. Golowich and D. Rolnick, Acyclic subgraphs of planar digraphs, Electronic Journal of Combinatorics 22(3):P3.7, 2015.
  22. *J.A. De Loera, S. Margulies, M. Pernpeintner, E. Riedl, D. Rolnick, G. Spencer, D. Stasi, and J. Swenson, Graph-coloring ideals: Nullstellensatz certificates, Groebner bases for chordal graphs, and hardness of Groebner bases, International Symposium on Symbolic and Algebraic Computation (ISSAC) 2015.
  23. *D. Rolnick and P. Venkataramana, On the growth of Stanley sequences, Discrete Mathematics 338(11):1928-1937, 2015.
  24. *D. Rolnick, The on-line degree Ramsey number of cycles, Discrete Mathematics 313(2):2084-2093, 2013.
  25. *D. Rolnick, Trees with an on-line degree Ramsey number of four, Electronic Journal of Combinatorics 18(1):P173, 2011.