Pinboard (mraginsky) https://pinboard.in/u:mraginsky/public/ recent bookmarks from mraginsky It’s not the thought that counts: Allostasis at the core of brain function: Neuron 2026-06-02T23:33:52+00:00 https://www.cell.com/neuron/fulltext/S0896-6273(25)00716-0?_returnURL=https%3A%2F%2Flinkinghub.elsevier.com%2Fretrieve%2Fpii%2FS0896627325007160%3Fshowall%3Dtrue mraginsky papers to-read neuroscience control-theory dynamical-systems cognition https://pinboard.in/ https://pinboard.in/u:mraginsky/b:0eecd28934b3/ [2410.01576] On incompressible flows in discrete networks and Shnirelman's inequality 2026-05-10T00:50:27+00:00 https://arxiv.org/abs/2410.01576 mraginsky papers to-read dynamical-systems PDEs https://pinboard.in/ https://pinboard.in/u:mraginsky/b:0d9ac4075df5/ [2605.01172] A Theory of Generalization in Deep Learning 2026-05-10T00:44:31+00:00 https://arxiv.org/abs/2605.01172 mraginsky papers to-read learning-theory machine-learning deep-learning dynamical-systems optimization neural-networks generalization-bounds https://pinboard.in/ https://pinboard.in/u:mraginsky/b:5ed6efa9c148/ On computing quantum waves exactly from classical action | Proceedings A | The Royal Society 2026-05-01T15:55:32+00:00 https://royalsocietypublishing.org/rspa/article/482/2336/20250413/481461/On-computing-quantum-waves-exactly-from-classical mraginsky papers to-read physics dynamical-systems quantum-mechanics color-me-skeptical https://pinboard.in/ https://pinboard.in/u:mraginsky/b:10c52d2df623/ The Market as a Creative Process | Economics & Philosophy | Cambridge Core 2026-04-18T21:19:33+00:00 https://www.cambridge.org/core/journals/economics-and-philosophy/article/market-as-a-creative-process/4A62A60230535D4A8553A7C26A184F56 mraginsky papers to-read economics dynamical-systems complex-systems process-philosophy evolution https://pinboard.in/ https://pinboard.in/u:mraginsky/b:7f64a7342065/ STRUCTURES Blog | Predicting the Future: From Cave Paintings to DynaMix 2026-04-18T21:18:09+00:00 https://structures.uni-heidelberg.de/blog/posts/2026_02/ mraginskyblogs dynamical-systems control-theory time-series neural-networks https://pinboard.in/ https://pinboard.in/u:mraginsky/b:02e81ead7f43/ [2512.24945] Dynamic response phenotypes and model discrimination in systems and synthetic biology 2026-01-06T03:50:39+00:00 https://arxiv.org/abs/2512.24945 mraginsky papers to-read systems-biology control-theory dynamical-systems https://pinboard.in/ https://pinboard.in/u:mraginsky/b:dbf668c42dc8/ For Differential Equations with r Parameters, 2r+1 Experiments Are Enough for Identification | Journal of Nonlinear Science 2025-11-14T03:26:20+00:00 https://link.springer.com/article/10.1007/s00332-002-0506-0 mraginsky papers to-read dynamical-systems differential-equations system-identification https://pinboard.in/ https://pinboard.in/u:mraginsky/b:cb57577cf584/ [2510.15511] Language Models are Injective and Hence Invertible 2025-11-05T16:01:19+00:00 https://arxiv.org/abs/2510.15511 mraginsky papers to-read large-language-models dynamical-systems neural-networks https://pinboard.in/ https://pinboard.in/u:mraginsky/b:b44b817515cc/ [2508.11990] Universal Learning of Nonlinear Dynamics 2025-10-22T16:19:25+00:00 https://arxiv.org/abs/2508.11990 mraginsky papers to-read system-identification control-theory learning-theory dynamical-systems https://pinboard.in/ https://pinboard.in/u:mraginsky/b:9164da4f209d/ The Symplectic Semigroup and Riccati Differential Equations | Journal of Dynamical and Control Systems 2025-10-15T15:41:07+00:00 https://link.springer.com/article/10.1007/s10450-006-9683-8 mraginsky papers to-read dynamical-systems control-theory differential-equations symplectic-geometry https://pinboard.in/ https://pinboard.in/u:mraginsky/b:adfbeaa3393e/ [2509.19601] Modular Machine Learning with Applications to Genetic Circuit Composition 2025-09-29T01:53:44+00:00 https://arxiv.org/abs/2509.19601 mraginsky papers to-read systems-biology control-theory dynamical-systems https://pinboard.in/ https://pinboard.in/u:mraginsky/b:cd5e939dcbbb/ [2209.08832] From microscopic to macroscopic scale equations: mean field, hydrodynamic and graph limits 2025-09-25T13:36:29+00:00 https://arxiv.org/abs/2209.08832 mraginsky papers to-read statistical-physics dynamical-systems interacting-particle-systems https://pinboard.in/ https://pinboard.in/u:mraginsky/b:b2fd1757e956/ From graph topology to ODE models for gene regulatory networks | PLOS One 2025-08-24T17:37:23+00:00 https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0235070 mraginsky papers to-read dynamical-systems systems-biology graph-theory networks genomics https://pinboard.in/ https://pinboard.in/u:mraginsky/b:a9f0df19d6f1/ The Peter Putnam Papers 2025-06-29T16:02:10+00:00 https://www.peterputnam.org/ mraginskypapers cognition neural-networks dynamical-systems ai https://pinboard.in/ https://pinboard.in/u:mraginsky/b:e9cc14716bd7/ Toward a mathematical theory of trajectory inference 2025-02-18T20:00:07+00:00 https://projecteuclid.org/journals/annals-of-applied-probability/volume-34/issue-1A/Toward-a-mathematical-theory-of-trajectory-inference/10.1214/23-AAP1969.full mraginsky papers to-read mathematical-biology dynamical-systems optimal-transportation SDEs https://pinboard.in/ https://pinboard.in/u:mraginsky/b:64c16c4c14ee/ [2409.12179] Computational Dynamical Systems 2025-01-20T21:17:07+00:00 https://arxiv.org/abs/2409.12179 mraginsky papers to-read computation dynamical-systems https://pinboard.in/ https://pinboard.in/u:mraginsky/b:443b5d7ab1e5/ [2406.19861] Operator World Models for Reinforcement Learning 2025-01-20T02:19:08+00:00 https://arxiv.org/abs/2406.19861 mraginsky papers to-read reinforcement-learning dynamical-systems optimization kernel-methods https://pinboard.in/ https://pinboard.in/u:mraginsky/b:7f2d5ffec7a5/ [2409.07401] Convergence of continuous-time stochastic gradient descent with applications to linear deep neural networks 2025-01-07T15:38:32+00:00 https://arxiv.org/abs/2409.07401 mraginsky papers to-read SDEs optimization gradient-flows learning-theory dynamical-systems https://pinboard.in/ https://pinboard.in/u:mraginsky/b:5a9d57c53afc/ Optimal interpolating and smoothing functional artificial neural networks (FANNs) based on a generalized fock space framework | Circuits, Systems, and Signal Processing 2024-12-27T14:03:53+00:00 https://link.springer.com/article/10.1007/BF01202856 mraginsky papers to-read neural-networks nonlinear-systems dynamical-systems control-theory filtering https://pinboard.in/ https://pinboard.in/u:mraginsky/b:05c0de74bb6d/ [2412.07438] Flows of vector fields and the Kalman Theorem 2024-12-15T21:09:53+00:00 https://arxiv.org/abs/2412.07438 mraginsky papers to-read control-theory dynamical-systems differential-geometry https://pinboard.in/ https://pinboard.in/u:mraginsky/b:0a41e9ddec66/ On the Mathematics of RNA Velocity I: Theoretical Analysis | bioRxiv 2024-12-09T19:23:32+00:00 https://www.biorxiv.org/content/10.1101/2020.09.19.304584v1 mraginsky papers to-read biology systems-biology cells genomics dynamical-systems https://pinboard.in/ https://pinboard.in/u:mraginsky/b:5e24c4613977/ A Dynamical Systems Perspective on Discrete Optimization 2024-08-22T15:57:20+00:00 https://proceedings.mlr.press/v211/guanchun23a.html mraginsky papers to-read dynamical-systems optimization statistical-physics https://pinboard.in/ https://pinboard.in/u:mraginsky/b:e7a2328fbf3e/ [2305.17628] Convex operator-theoretic methods in stochastic control 2024-08-20T11:05:16+00:00 https://arxiv.org/abs/2305.17628 mraginsky papers to-read control-theory dynamical-systems optimization functional-analysis https://pinboard.in/ https://pinboard.in/u:mraginsky/b:c36d6ed9e02d/ [2304.03519] Robust data-driven control for nonlinear systems using the Koopman operator 2024-08-20T10:58:37+00:00 https://arxiv.org/abs/2304.03519 mraginsky papers to-read control-theory dynamical-systems Koopman-operators https://pinboard.in/ https://pinboard.in/u:mraginsky/b:1b6cb0cfd335/ [2404.18380] Dynamic Global Feedback Stabilization: why do the twist? 2024-08-13T20:11:02+00:00 https://arxiv.org/abs/2404.18380 mraginsky papers to-read control-theory dynamical-systems feedback geometry topology https://pinboard.in/ https://pinboard.in/u:mraginsky/b:1e6f0dfe9c79/ Control Using Logic-Based Switching | SpringerLink 2024-08-12T18:51:27+00:00 https://link.springer.com/book/10.1007/BFb0036078 mraginsky books control-theory adaptive-systems dynamical-systems https://pinboard.in/ https://pinboard.in/u:mraginsky/b:a31bfff8e73a/ The neuron as a direct data-driven controller | PNAS 2024-06-25T02:10:00+00:00 https://www.pnas.org/doi/10.1073/pnas.2311893121 mraginsky papers to-read neuroscience control-theory dynamical-systems https://pinboard.in/ https://pinboard.in/u:mraginsky/b:0fe5a5c7ec9e/ Formalising the role of behaviour in neuroscience - Piantadosi - European Journal of Neuroscience - Wiley Online Library 2024-06-17T19:59:17+00:00 https://onlinelibrary.wiley.com/doi/10.1111/ejn.16372 mraginsky papers to-read neuroscience control-theory dynamical-systems state-space-models https://pinboard.in/ https://pinboard.in/u:mraginsky/b:b2dcbfcf9013/ On the Import of Constraints in Complex Dynamical Systems | Foundations of Science 2024-04-15T02:08:40+00:00 https://link.springer.com/article/10.1007/s10699-012-9304-9 mraginsky papers to-read dynamical-systems philosophy-of-engineering physics complex-systems https://pinboard.in/ https://pinboard.in/u:mraginsky/b:5ff28afc08c9/ [2402.01032] Repeat After Me: Transformers are Better than State Space Models at Copying 2024-02-07T16:20:02+00:00 https://arxiv.org/abs/2402.01032 mraginsky papers to-read dynamical-systems transformers https://pinboard.in/ https://pinboard.in/u:mraginsky/b:1297f3039ff1/ Feedback Maximum Principle for Ensemble Control of Local Continuity Equations: An Application to Supervised Machine Learning | IEEE Journals & Magazine | IEEE Xplore 2024-01-14T21:02:13+00:00 https://ieeexplore.ieee.org/abstract/document/9454440 mraginsky papers to-read dynamical-systems control-theory ODEs machine-learning https://pinboard.in/ https://pinboard.in/u:mraginsky/b:2028fc5e7330/ [2312.12903] A Minimal Control Family of Dynamical Syetem for Universal Approximation 2023-12-23T20:19:04+00:00 https://arxiv.org/abs/2312.12903 mraginsky papers to-read neural-networks dynamical-systems differential-equations control-theory https://pinboard.in/ https://pinboard.in/u:mraginsky/b:f238f721525e/ [2212.13628] Functional Expansions 2023-11-29T19:11:59+00:00 https://arxiv.org/abs/2212.13628 mraginsky papers have-read stochastic-analysis functional-analysis finance dynamical-systems https://pinboard.in/ https://pinboard.in/u:mraginsky/b:e14055ffa1bf/ Workshop on Statistical Physics of Inference and Control Theory, Granada 2012 - VideoLectures - VideoLectures.NET 2023-08-09T21:01:56+00:00 http://videolectures.net/cyberstat2012_granada/ mraginskystatistical-physics inference information control-theory learning dynamical-systems https://pinboard.in/ https://pinboard.in/u:mraginsky/b:030cd6bd49c8/ Controllability, integrability and ergodicity | SpringerLink 2023-07-13T21:43:09+00:00 https://link.springer.com/chapter/10.1007/3-540-36589-3_17 mraginsky papers to-read control-theory dynamical-systems ergodic-theory https://pinboard.in/ https://pinboard.in/u:mraginsky/b:25c08d304c7f/ [2305.18288] Linearizability of flows by embeddings 2023-05-30T02:42:46+00:00 https://arxiv.org/abs/2305.18288 mraginsky papers to-read dynamical-systems Koopman-operators https://pinboard.in/ https://pinboard.in/u:mraginsky/b:b93cc5516ec1/ On strong anticipation - ScienceDirect 2023-05-04T16:41:49+00:00 https://www.sciencedirect.com/science/article/abs/pii/S1389041709000163?casa_token=8dkZ1O1iNBcAAAAA:gnuocqU5jszqBuwnBv1BYYua466pUhmQXOokW-3DOCA_-v5GNHpSCvptgCXuxYcYizauW6_Qzt8 mraginsky papers to-read control-theory dynamical-systems ecological-psychology cognitive-science https://pinboard.in/ https://pinboard.in/u:mraginsky/b:a614ef1065ba/ [2301.06632] Asymptotic normality and optimality in nonsmooth stochastic approximation 2023-01-18T09:05:44+00:00 https://arxiv.org/abs/2301.06632 mraginsky papers to-read heard-the-talk optimization dynamical-systems nonsmooth-geometry stratification-theory https://pinboard.in/ https://pinboard.in/u:mraginsky/b:c9232da98331/ [2206.04030] High-dimensional limit theorems for SGD: Effective dynamics and critical scaling 2023-01-16T09:27:07+00:00 https://arxiv.org/abs/2206.04030 mraginsky papers to-read heard-the-talk optimization dynamical-systems machine-learning gradient-flows https://pinboard.in/ https://pinboard.in/u:mraginsky/b:1e2cc35c0d94/ [2205.14027] Learning Dynamical Systems via Koopman Operator Regression in Reproducing Kernel Hilbert Spaces 2022-10-25T12:31:35+00:00 https://arxiv.org/abs/2205.14027 mraginsky papers to-read heard-the-talk machine-learning kernel-methods dynamical-systems Koopman-operators https://pinboard.in/ https://pinboard.in/u:mraginsky/b:d99604a1f5bb/ Adaptive Checkpoint Adjoint Method for Gradient Estimation in Neural ODE 2022-10-22T15:36:25+00:00 https://proceedings.mlr.press/v119/zhuang20a.html mraginsky papers to-read neural-networks machine-learning ODEs dynamical-systems https://pinboard.in/ https://pinboard.in/u:mraginsky/b:566a12bbe273/ Dynamical Systems and Sheaves | SpringerLink 2022-10-03T02:57:57+00:00 https://link.springer.com/article/10.1007/s10485-019-09565-x mraginsky to-read type-theory control-theory categories dynamical-systems functional-programming logic papers https://pinboard.in/ https://pinboard.in/u:mraginsky/b:3ee6ce48d6c5/ [1710.10258] Temporal Type Theory: A topos-theoretic approach to systems and behavior 2022-10-03T02:50:36+00:00 https://arxiv.org/abs/1710.10258 mraginsky books to-read type-theory control-theory categories dynamical-systems functional-programming logic https://pinboard.in/ https://pinboard.in/u:mraginsky/b:66d37e1343ca/ Isabelle Gallagher, "From Newton to Navier–Stokes, or how to connect fluid mechanics equations from microscopic to macroscopic scales" 2022-08-10T16:52:28+00:00 https://www.ams.org/journals/bull/2019-56-01/S0273-0979-2018-01650-9/ mraginsky papers to-read fluid-mechanics dynamical-systems physics PDEs https://pinboard.in/ https://pinboard.in/u:mraginsky/b:21aa3d116955/ [2204.12786] Machines of finite depth: towards a formalization of neural networks 2022-08-02T16:31:20+00:00 https://arxiv.org/abs/2204.12786 mraginsky papers to-read neural-networks computation dynamical-systems systems https://pinboard.in/ https://pinboard.in/u:mraginsky/b:bf8b501d87fa/ EUDML  |  Some optimal control applications of real-analytic stratifications and desingularization 2022-08-02T16:25:50+00:00 https://eudml.org/doc/208885 mraginskypapers to-read geometry control-theory dynamical-systems https://pinboard.in/ https://pinboard.in/u:mraginsky/b:8b178b043c07/ [2204.11900] Towards a Geometry and Analysis for Bayesian Mechanics 2022-08-02T16:23:25+00:00 https://arxiv.org/abs/2204.11900 mraginsky papers to-read Bayesian-inference differential-geometry complex-systems adaptive-systems dynamical-systems statistical-physics https://pinboard.in/ https://pinboard.in/u:mraginsky/b:d21d4b8939d5/ Stochastic systems in Riemannian manifolds | SpringerLink 2022-08-02T16:04:50+00:00 https://link.springer.com/article/10.1007/BF00933032 mraginsky papers to-read stochastic-analysis differential-geometry SDEs dynamical-systems probability https://pinboard.in/ https://pinboard.in/u:mraginsky/b:b60dbee2d2c8/ The algorithmic origins of life | Journal of The Royal Society Interface 2022-08-02T16:00:01+00:00 https://royalsocietypublishing.org/doi/10.1098/rsif.2012.0869 mraginsky papers to-read biogenesis information-theory algorithms causality control-theory dynamical-systems cybernetics https://pinboard.in/ https://pinboard.in/u:mraginsky/b:053e8aa6fdff/ [2207.12395] Statistical Inference with Stochastic Gradient Algorithms 2022-07-26T21:02:05+00:00 https://arxiv.org/abs/2207.12395 mraginsky papers to-read statistical-learning optimization dynamical-systems sampling https://pinboard.in/ https://pinboard.in/u:mraginsky/b:2223fcf2d3c3/ The Barron Space and the Flow-Induced Function Spaces for Neural Network Models | SpringerLink 2022-06-28T19:54:59+00:00 https://link.springer.com/article/10.1007/s00365-021-09549-y mraginsky papers have-read neural-networks dynamical-systems machine-learning approximation-theory function-approximation https://pinboard.in/ https://pinboard.in/u:mraginsky/b:cd69a86cb403/ [2206.06227] Convergence for score-based generative modeling with polynomial complexity 2022-06-14T09:48:03+00:00 https://arxiv.org/abs/2206.06227 mraginsky papers to-read generative-models SDEs learning-theory optimization dynamical-systems https://pinboard.in/ https://pinboard.in/u:mraginsky/b:3ba5042fb111/ [2205.09241] Neural ODE Control for Trajectory Approximation of Continuity Equation 2022-05-23T15:18:53+00:00 https://arxiv.org/abs/2205.09241 mraginsky papers to-read control-theory dynamical-systems ODEs SDEs neural-networks machine-learning https://pinboard.in/ https://pinboard.in/u:mraginsky/b:0389d5764128/ [2101.12606] Dissipativity and optimal control 2022-03-22T20:14:20+00:00 https://arxiv.org/abs/2101.12606 mraginsky papers to-read optimization control-theory dynamical-systems https://pinboard.in/ https://pinboard.in/u:mraginsky/b:2e7dcf0b4bf5/ [2104.05278] Neural ODE control for classification, approximation and transport 2021-07-14T17:31:29+00:00 https://arxiv.org/abs/2104.05278 mraginsky papers to-read neural-networks ODEs dynamical-systems control-theory https://pinboard.in/ https://pinboard.in/u:mraginsky/b:5bafc70f1ac0/ [2006.10330] A Shooting Formulation of Deep Learning 2021-05-03T22:22:04+00:00 https://arxiv.org/abs/2006.10330 mraginsky papers to-read machine-learning neural-networks ODEs control-theory dynamical-systems https://pinboard.in/ https://pinboard.in/u:mraginsky/b:6f5ab0d954eb/ [2002.08071] Dissecting Neural ODEs 2021-05-03T22:21:23+00:00 https://arxiv.org/abs/2002.08071 mraginsky papers have-read machine-learning neural-networks ODEs dynamical-systems https://pinboard.in/ https://pinboard.in/u:mraginsky/b:a6cb7a07ee6d/ Fundamental bounds on learning performance in neural circuits | PNAS 2021-04-14T15:36:43+00:00 https://www.pnas.org/content/116/21/10537 mraginsky papers to-read neuroscience neural-networks learning control-theory dynamical-systems biology https://pinboard.in/ https://pinboard.in/u:mraginsky/b:05d5179c4894/ A Theory of the Epigenesis of Neuronal Networks by Selective Stabilization of Synapses | PNAS 2021-04-14T15:13:41+00:00 https://www.pnas.org/content/70/10/2974 mraginsky papers to-read neuroscience biology learning control-theory dynamical-systems neural-networks https://pinboard.in/ https://pinboard.in/u:mraginsky/b:0715924cac17/ [2104.05508] Noether: The More Things Change, the More Stay the Same 2021-04-14T15:03:31+00:00 https://arxiv.org/abs/2104.05508 mraginsky papers to-read deep-learning neural-networks gradient-flows dynamical-systems https://pinboard.in/ https://pinboard.in/u:mraginsky/b:2b1bc90b677e/ Depth-Width Trade-offs for ReLU Networks via Sharkovsky's Theorem | OpenReview 2021-02-19T17:28:30+00:00 https://openreview.net/forum?id=BJe55gBtvH mraginskypapers to-read neural-networks deep-learning dynamical-systems https://pinboard.in/ https://pinboard.in/u:mraginsky/b:c2760284dafa/ Frontiers | Homeostasis: The Underappreciated and Far Too Often Ignored Central Organizing Principle of Physiology | Physiology 2021-01-02T02:48:56+00:00 https://www.frontiersin.org/articles/10.3389/fphys.2020.00200/full mraginsky to-read papers cybernetics physiology biology control-theory dynamical-systems https://pinboard.in/ https://pinboard.in/u:mraginsky/b:70dfcf02ea25/ Deep Implicit Layers - Neural ODEs, Deep Equilibirum Models, and Beyond 2020-12-07T16:23:42+00:00 https://implicit-layers-tutorial.org/ mraginsky machine-learning neural-networks deep-learning dynamical-systems ODEs generative-models https://pinboard.in/ https://pinboard.in/u:mraginsky/b:9e151207031f/ [2007.06007] Universal Approximation Power of Deep Neural Networks via Nonlinear Control Theory 2020-08-19T18:45:41+00:00 https://arxiv.org/abs/2007.06007 mraginsky papers to-read deep-learning neural-networks dynamical-systems control-theory differential-equations https://pinboard.in/ https://pinboard.in/u:mraginsky/b:50632fd10d08/ [1807.08351] Data Assimilation: The Schrödinger Perspective 2020-07-20T20:22:22+00:00 https://arxiv.org/abs/1807.08351 mraginsky papers have-read filtering MCMC Bayesian-inference dynamical-systems PDEs stochastic-control https://pinboard.in/ https://pinboard.in/u:mraginsky/b:86d2f91d7b18/ Accelerated Flow for Probability Distributions 2020-07-20T20:19:46+00:00 http://proceedings.mlr.press/v97/taghvaei19a.html mraginsky papers to-read machine-learning sampling dynamical-systems https://pinboard.in/ https://pinboard.in/u:mraginsky/b:d3babed75d43/ [2005.10963] Stochastic control liasons: Richard Sinkhorn meets Gaspard Monge on a Schroedinger bridge 2020-07-20T20:18:38+00:00 https://arxiv.org/abs/2005.10963 mraginsky papers to-read stochastic-control optimal-transportation dynamical-systems dynamic-programming PDEs https://pinboard.in/ https://pinboard.in/u:mraginsky/b:7f29f1ad8914/ [math/9906212] Proof of the gradient conjecture of R. Thom 2020-07-20T20:17:35+00:00 https://arxiv.org/abs/math/9906212 mraginsky papers to-read dynamical-systems differential-equations geometry https://pinboard.in/ https://pinboard.in/u:mraginsky/b:d521a6357ac3/ [2006.06462] Deep Differential System Stability -- Learning advanced computations from examples 2020-07-20T20:17:00+00:00 https://arxiv.org/abs/2006.06462 mraginsky papers to-read machine-learning deep-learning dynamical-systems control-theory state-space-models stability https://pinboard.in/ https://pinboard.in/u:mraginsky/b:ca3ba9610638/