Publications

See also my Google Scholar.

Conference Publications

  1. M. Teng, A. Elmustafa, B. Akera, Y. Bengio, H. Radi Abdelwahed, H. Larochelle, D. Rolnick, SatBird: A dataset for bird species distribution modeling using remote sensing and citizen science data, Conference on Neural Information Processing Systems (NeurIPS) 2023.
  2. J. Kaltenborn, C.E.E. Lange, V. Ramesh, P. Brouillard, Y. Gurwicz, J. Runge, P. Nowack, D. Rolnick, ClimateSet: A large-scale climate model dataset for machine learning, Conference on Neural Information Processing Systems (NeurIPS) 2023.
  3. M. Mueller, T. Vlaar, D. Rolnick, M. Hein, Normalization layers are all that sharpness-aware minimization needs, Conference on Neural Information Processing Systems (NeurIPS) 2023.
  4. A. Duval, V. Schmidt, A. Hernández-García, F.D. Malliaros, Y. Bengio, S. Miret, D. Rolnick, FAENet: Frame Averaging Equivariant GNNs for materials modeling, International Conference on Machine Learning (ICML) 2023.
  5. G. Iyer, B. Hanin, D. Rolnick, Maximal initial learning rates in deep ReLU networks, International Conference on Machine Learning (ICML) 2023.
  6. E. Grigsby, K. Lindsey, D. Rolnick, Hidden symmetries of ReLU networks, International Conference on Machine Learning (ICML) 2023.
  7. C. Boine, D. Rolnick, General purpose AI systems in the AI Act: trying to fit a square peg into a round hole, We Robot 2023 (best paper).
  8. R.D. Lange, J. Matelsky, X. Wang, D. Kwok, D. Rolnick, K.P. Kording, Deep networks as paths on the manifold of neural representations, Proceedings of the Workshop on Topology, Algebra, and Geometry in Machine Learning (TAG-ML) 2023.
  9. A.S. Luccioni, D. Rolnick, Bugs in the data: How ImageNet misrepresents biodiversity, AAAI 2023.
  10. S. Cohan, N.H. Kim, D. Rolnick, M. van de Panne, Understanding the evolution of linear regions in deep reinforcement learning, Conference on Neural Information Processing Systems (NeurIPS) 2022.
  11. B. Hanin, R. Jeong, D. Rolnick, Deep ReLU networks preserve expected length, International Conference on Learning Representations (ICLR) 2022.
  12. S. Topan, D. Rolnick, X. Si, Techniques for symbol grounding with SATNet, Conference on Neural Information Processing Systems (NeurIPS) spotlight, 2021.
  13. S. Rühling Cachay, V. Ramesh, J.N.S. Cole, H. Barker, D. Rolnick, ClimART: A benchmark dataset for emulating atmospheric radiative transfer in weather and climate models, Conference on Neural Information Processing Systems (NeurIPS), 2021.
  14. P.L. Donti, D. Rolnick, J.Z. Kolter, DC3: A learning method for optimization with hard constraints, International Conference on Learning Representations (ICLR) 2021.
  15. D. Rolnick, K.P. Körding, Reverse-engineering deep ReLU networks, International Conference on Machine Learning (ICML) 2020.
  16. D. Rolnick, A. Ahuja, J. Schwarz, T.P. Lillicrap, G. Wayne, Experience replay for continual learning, Conference on Neural Information Processing Systems (NeurIPS) 2019.
  17. B. Hanin, D. Rolnick, Deep ReLU networks have surprisingly few activation patterns, Conference on Neural Information Processing Systems (NeurIPS) 2019.
  18. B. Hanin, D. Rolnick, Complexity of linear regions in deep networks, International Conference on Machine Learning (ICML) 2019.
  19. D. Rolnick, J. Pouget-Abadie, K. Aydin, S. Kamali, V. Mirrokni, A. Najmi, Randomized experimental design via geographic clustering, Conference on Knowledge Discovery and Data Mining (KDD) 2019.
  20. A. Benjamin, D. Rolnick, K. Kording, Measuring and regularizing networks in function space, International Conference on Learning Representations (ICLR) 2019.
  21. 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, Conference on Computer Vision and Pattern Recognition (CVPR) 2019.
  22. B. Hanin, D. Rolnick, How to start training: The effect of initialization and architecture, Conference on Neural Information Processing Systems (NeurIPS) 2018.
  23. D. Rolnick, M.Tegmark, The power of deeper networks for expressing natural functions, International Conference on Learning Representations (ICLR) 2018.
  24. 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.

Journal Publications

  1. A. Duval, V. Schmidt, A. Hernández-García, S. Miret, Y. Bengio, D. Rolnick, PhAST: Physics-Aware, Scalable, and Task-specific GNNs for accelerated catalyst design, Journal of Machine Learning Research (JMLR), 2024.
  2. P. Harder, Q. Yang, V. Ramesh, P. Sattigeri, A. Hernandez-Garcia, C. Watson, D. Szwarcman, D. Rolnick, Hard-Constrained Deep Learning for Climate Downscaling, Journal of Machine Learning Research (JMLR), 2023.
  3. R.L. Fischman, J.B. Ruhl, B.R. Forester, T.M. Lama, M. Kardos, G. Aguilar Rojas, N.A. Robinson, P.D. Shirey, G.A. Lamberti, A.W. Ando, S. Palumbi, M. Wara, M.W. Schwartz, M.A. Williamson, T. Berger-Wolf, S. Beery, D. Rolnick, J. Kitzes, D. Thau, D. Tuia, D. Rubenstein, C.R. Hickman, J. Thorstenson, G.E. Kaebnick, J.P. Collins, A. Jayaram, T. Deleuil, Y. Zhao, A landmark environmental law looks ahead, Science 382(6677), 2023.
  4. L. Kaack, P.L. Donti, E. Strubell, G. Kamiya, F. Creutzig, D. Rolnick, Aligning artificial intelligence with climate change mitigation, Nature Climate Change, 2022.
  5. R.D. Lange, D. Rolnick, K.P. Kording, Clustering units in neural networks: upstream vs downstream information, Transactions on Machine Learning Research (TMLR), 2022.
  6. D. Rolnick, P.L. Donti, L.H. Kaack, K. Kochanski, A. Lacoste, K. Sankaran, A.S. Ross, N. Milojevic-Dupont, N. Jaques, A. Waldman-Brown, A. Luccioni, T. Maharaj, E.D. Sherwin, S.K. Mukkavilli, K.P. Kording, C. Gomes, A.Y. Ng, D. Hassabis, J.C. Platt, F. Creutzig, J. Chayes, Y. Bengio, Tackling climate change with machine learning, ACM Computing Surveys 55(2), 2022.
  7. P. Chuard, J. Garard, K. Schulz, N. Kumarasinghe, D. Rolnick, D. Matthews, A portrait of the different configurations between digitally-enabled innovations and climate governance, Earth System Governance 13, 2022.
  8. F. Creutzig, D. Acemoglu, X. Bai, P.N. Edwards, M.J. Hintz, L.H. Kaack, S. Kilkis, S. Kunkel, A. Luers, N. Milojevic-Dupont, D. Rejeski, J. Renn, D. Rolnick, C. Rosol, D. Russ, T. Turnbull, E. Verdolini, F. Wagner, C. Wilson, A. Zekar, M. Zumwald, Digitalization and the anthropocene, Annual Review of Environment and Resources 47, 2022.
  9. L.A. Reisch, L. Joppa, P. Howson, A. Gil, P. Alevizou, N. Michaelidou, R. Appiah-Campbell, T. Santarius, S. Köhler, M. Pizzol, P.-J. Schweizer, D. Srinivasan, L.H. Kaack, P.L. Donti, D. Rolnick, Digitizing a sustainable future, One Earth 4(6):768-771, 2021.
  10. C. Hillar, R. Taubman, T. Chan, D. Rolnick, Hidden hypergraphs, error-correcting codes, and critical learning in Hopfield networks, Entropy, 2021.
  11. D. Rolnick, E. Dyer, Generative models and abstractions for large-scale neuroanatomy datasets, Current Opinion in Neurobiology, 2019.
  12. G. Spencer, D. Rolnick, On the robust hardness of Gröbner basis computation, Journal of Pure and Applied Algebra 223(5):2080-2100, 2019.
  13. H. Lin, M. Tegmark, D. Rolnick, Why does deep and cheap learning work so well?, Journal of Statistical Physics 168(6):1223-1247, 2017.
  14. D. Rolnick, P. Soberón, Quantitative (p,q)-theorems in combinatorial geometry, Discrete Mathematics 340(10):2516-2527, 2017.
  15. 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.
  16. 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.
  17. D. Rolnick, On the classification of Stanley sequences, European Journal of Combinatorics 59:51-70, 2017.
  18. R.A. Moy and D. Rolnick, Novel structures in Stanley sequences, Discrete Mathematics 339(2):689-698, 2016.
  19. N. Golowich and D. Rolnick, Acyclic subgraphs of planar digraphs, Electronic Journal of Combinatorics 22(3):P3.7, 2015.
  20. D. Rolnick and P. Venkataramana, On the growth of Stanley sequences, Discrete Mathematics 338(11):1928-1937, 2015.
  21. D. Rolnick, The on-line degree Ramsey number of cycles, Discrete Mathematics 313(2):2084-2093, 2013.
  22. D. Rolnick, Trees with an on-line degree Ramsey number of four, Electronic Journal of Combinatorics 18(1):P173, 2011.

Technical Reports and Book Chapters

  1. S. Koseki, S. Jameson, G. Farnadi, D. Rolnick, C. Régis, J.-L. Denis, et al., AI & cities: Risks, applications and governance, UN Habitat, 2022.
  2. D. Rolnick, Chapter 10 – Insights: AI and decarbonisation in O. Inderwildi, M. Kraft, eds. Intelligent Decarbonisation, Springer 2022.
  3. P. Clutton-Brock, D. Rolnick, P.L. Donti, L.H. Kaack, T. Maharaj, A. Luccioni, H. Prasanna Das, C. Hodes, V. Dignum, M. Kwiatkowska, R. Chatila, N. Miailhe, Climate change and AI: Recommendations for government action, Global Partnership on AI (GPAI), 2021.
  4. L.H. Kaack, P.L. Donti, E. Strubell, D. Rolnick, Artificial Intelligence and climate change: Opportunities, considerations, and policy levers to align AI with climate change goals, Heinrich Böll Foundation E-Paper, 2020.

Preprints and Workshop Papers

  1. D. Rolnick, A. Aspuru-Guzik, S. Beery, B. Dilkina, P.L. Donti, M. Ghassemi, H. Kerner, C. Monteleoni, E. Rolf, M. Tambe, A. White, Application-driven innovation in machine learning, preprint arXiv:2403.17381, 2024.
  2. E. Sharma, D. Kwok, T. Denton, D.M. Roy, D. Rolnick, G.K. Dziugaite, Simultaneous linear connectivity of neural networks modulo permutation, preprint arXiv:2404.06498, 2024.
  3. H. Radi Abdelwahed, M. Teng, D. Rolnick, Predicting species occurrence patterns from partial observations, preprint arXiv:2403.18028, 2024.
  4. N. Carlini, D. Paleka, K. Dvijotham, T. Steinke, J. Hayase, A.F. Cooper, K. Lee, M. Jagielski, M. Nasr, A. Conmy, E. Wallace, D. Rolnick, F. Tramèr, Stealing part of a production language model, preprint arXiv:2403.0663, 2024.
  5. D. Kwok, N. Anand, J. Frankle, G.K. Dziugaite, D. Rolnick, Dataset difficulty and the role of inductive bias, preprint arXiv:2401.01867, 2024.
  6. N.I. Bountos, A. Ouaknine, D. Rolnick, FoMo-Bench: a multi-modal, multi-scale and multi-task forest monitoring benchmark for remote sensing foundation models, preprint arXiv:2312.10114, 2023.
  7. A. Ouaknine, T. Kattenborn, E. Laliberté, D. Rolnick, OpenForest: A data catalogue for machine learning in forest monitoring, preprint arXiv:2311.00277, 2023.
  8. A. Carbonero, A. Duval, V. Schmidt, S. Miret, A. Hernández-García, Y. Bengio, D. Rolnick, On the importance of catalyst-adsorbate geometric relative information when predicting relaxed energy, NeurIPS Workshop on AI for Accelerated Materials Design, 2023.
  9. A. Jain, F. Cunha, M. Bunsen, L. Pasi, A. Viklund, M. Larrivée, D. Rolnick, A machine learning pipeline for automated insect monitoring, NeurIPS Workshop on Tackling Climate Change with Machine Learning, 2023.
  10. C. Winkler, P. Harder, D. Rolnick, Climate variable downscaling with conditional normalizing flows, NeurIPS Workshop on Tackling Climate Change with Machine Learning, 2023.
  11. J. Boussard, C. Nagda, J. Kaltenborn, C. Lange, Y. Gurwicz, P. Nowack, D. Rolnick, Towards causal representations of climate model data, NeurIPS Workshop on Tackling Climate Change with Machine Learning, 2023.
  12. Y. Chen, D. Rolnick, Understanding insect range shifts with out-of-distribution detection, NeurIPS Workshop on Tackling Climate Change with Machine Learning, 2023.
  13. J. González-Abad, Á. Hernández-García, P. Harder, D. Rolnick, J.M. Gutiérrez, Multi-variable Hard Physical Constraints for Climate Model Downscaling, preprint arXiv:2308.01868, 2023.
  14. G. Tseng, I. Zvonkov, M. Purohit, D. Rolnick, H. Kerner, Lightweight, pre-trained Transformers for remote sensing timeseries, preprint arXiv:2304.14065, 2023.
  15. Q. Yang, P. Harder, V. Ramesh, A. Hernandez-Garcia, D. Szwarcman, P. Sattigeri, C.D. Watson, D. Rolnick, Fourier neural operators for arbitrary resolution climate data downscaling, preprint arXiv:2305.14452, 2023.
  16. G. Tseng, K. Sinkovics, T. Watsham, D. Rolnick, T.C. Walters, Semi-supervised object detection for agriculture, AAAI workshop on AI for Agriculture and Food Systems, 2023.
  17. G. Kerg, S. Mittal, D. Rolnick, Y. Bengio, B. Richards, G. Lajoie, On neural architecture inductive biases for relational tasks, preprint arXiv:2206.05056, 2022.
  18. G. Tseng, H. Kerner, D. Rolnick, TIML: Task-Informed Meta-Learning for agriculture, preprint arXiv:2202.02124, 2022.
  19. M. Lin, D. Rolnick, Detecting abandoned oil wells using machine learning and semantic segmentation, spotlight at NeurIPS Workshop on Tackling Climate Change with Machine Learning, 2021.
  20. M. Skreta, S. Luccioni, D. Rolnick, Spatiotemporal features improve fine-grained butterfly image classification, spotlight at NeurIPS Workshop on Tackling Climate Change with Machine Learning, 2020.
  21. R. Farhoodi, D. Rolnick, K. Kording, Neuron dendrograms uncover asymmetrical motifs, Computational and Systems Neuroscience (Cosyne) 2018.
  22. D. Rolnick, A. Veit, S. Belongie, N. Shavit, Deep learning is robust to massive label noise, preprint arXiv:1705.10694, 2017.
  23. D. Rolnick, Y. Meirovitch, T. Parag, H. Pfister, V. Jain, J.W. Lichtman, E.S. Boyden, N. Shavit, Morphological error detection in 3D segmentations, Computational and Systems Neuroscience (Cosyne) 2018.
  24. D. Rolnick, J. Bernstein, I. Dasgupta, H. Sompolinsky, Markov transitions between attractor states in a recurrent neural network, Computational and Systems Neuroscience (Cosyne) 2017.
  25. 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.
  26. D. Rolnick, P. Soberón, Algorithmic aspects of Tverberg’s theorem, preprint arXiv:1601.03083, 2016.