Publication
Found 142 results
Author Title Type [ Year
] Filters: First Letter Of Last Name is R [Clear All Filters]
What if Eye..? Computationally Recreating Vision Evolution. arXiv (2025). at <https://arxiv.org/abs/2501.15001>
2501.15001v1.pdf (5.2 MB)
2501.15001v1.pdf (5.2 MB) Assumption violations in causal discovery and the robustness of score matching. 37th Conference on Neural Information Processing Systems (NeurIPS 2023) (2024). at <https://proceedings.neurips.cc/paper_files/paper/2023/file/93ed74938a54a73b5e4c52bbaf42ca8e-Paper-Conference.pdf>
On Generalization Bounds for Neural Networks with Low Rank Layers. (2024). CBMM-Memo-151.pdf (697.31 KB)
CBMM-Memo-151.pdf (697.31 KB) RESPRECT: Speeding-up Multi-Fingered Grasping With Residual Reinforcement LearningRESPRECT: Speeding-Up Multi-Fingered Grasping With Residual Reinforcement Learning_supp1-3363532.mp4. IEEE Robotics and Automation Letters 9, 3045 - 3052 (2024).
Top-tuning: A study on transfer learning for an efficient alternative to fine tuning for image classification with fast kernel methods. Image and Vision Computing 142, 104894 (2024).
An adversarial collaboration protocol for testing contrasting predictions of global neuronal workspace and integrated information theory. PLOS ONE 18, e0268577 (2023). journal.pone_.0268577.pdf (1.99 MB)
journal.pone_.0268577.pdf (1.99 MB) An adversarial collaboration to critically evaluate theories of consciousness. bioRxiv (2023). doi:https://doi.org/10.1101/2023.06.23.546249
Catalyzing next-generation Artificial Intelligence through NeuroAIAbstract. Nature Communications 14, (2023).
Cross-task specificity and within-task invariance of cognitive control processes. Cell Reports 42, 111919 (2023). PIIS2211124722018174.pdf (3.97 MB)
PIIS2211124722018174.pdf (3.97 MB) Decoding of human identity by computer vision and neuronal vision. Scientific Reports 13, (2023). s41598-022-26946-w.pdf (1.88 MB)
s41598-022-26946-w.pdf (1.88 MB) Decoding of human identity by computer vision and neuronal visionAbstract. Scientific Reports 13, (2023).
Dynamics in Deep Classifiers trained with the Square Loss: normalization, low rank, neural collapse and generalization bounds. Research (2023). doi:10.34133/research.0024 research.0024.pdf (4.05 MB)
research.0024.pdf (4.05 MB) Estimating Koopman operators with sketching to provably learn large scale dynamical systems. 37th Conference on Neural Information Processing Systems (NeurIPS 2023) (2023). at <https://proceedings.neurips.cc/paper_files/paper/2023/file/f3d1e34a15c0af0954ae36a7f811c754-Paper-Conference.pdf>
Fast iterative regularization by reusing dataAbstract. Journal of Inverse and Ill-posed Problems (2023). doi:10.1515/jiip-2023-0009
Feature learning in deep classifiers through Intermediate Neural Collapse. (2023). Feature_Learning_memo.pdf (2.16 MB)
Feature_Learning_memo.pdf (2.16 MB) For interpolating kernel machines, minimizing the norm of the ERM solution maximizes stability. Analysis and Applications 21, 193 - 215 (2023).
For interpolating kernel machines, minimizing the norm of the ERM solution maximizes stability. Analysis and Applications 21, 193 - 215 (2023).
Forward learning with top-down feedback: empirical and analytical characterization. arXiv (2023). at <https://arxiv.org/abs/2302.05440>
Heteroscedastic Gaussian Processes and Random Features: Scalable Motion Primitives with Guarantees. 7th Conference on Robot Learning (CoRL 2023 (2023). at <https://proceedings.mlr.press/v229/caldarelli23a/caldarelli23a.pdf>
Implicit regularization with strongly convex bias: Stability and acceleration. Analysis and Applications 21, 165 - 191 (2023).
The Janus effects of SGD vs GD: high noise and low rank. (2023). Updated with appendix showing empirically that the main results extend to deep nonlinear networks (2.95 MB) Small updates...typos... (616.82 KB)
Updated with appendix showing empirically that the main results extend to deep nonlinear networks (2.95 MB) Small updates...typos... (616.82 KB) The Janus effects of SGD vs GD: high noise and low rank. (2023). Updated with appendix showing empirically that the main results extend to deep nonlinear networks (2.95 MB) Small updates...typos... (616.82 KB)
Updated with appendix showing empirically that the main results extend to deep nonlinear networks (2.95 MB) Small updates...typos... (616.82 KB) An Optimal Structured Zeroth-order Algorithm for Non-smooth Optimization. 37th Conference on Neural Information Processing Systems (NeurIPS 2023) (2023). at <https://proceedings.neurips.cc/paper_files/paper/2023/file/7429f4c1b267cf619f28c4d4f1532f99-Paper-Conference.pdf>