Pinboard (cshalizi) https://pinboard.in/u:cshalizi/public/ recent bookmarks from cshalizi [2606.13280] Generalization Bounds for Transformer-Based Next-Token Prediction in a Language Model 2026-06-17T16:26:17+00:00 https://arxiv.org/abs/2606.13280 cshalizi to:NB to_read learning_theory natural_language_processing large_language_models_(so_called) via:mraginsky https://pinboard.in/ https://pinboard.in/u:cshalizi/b:87e01de8c417/ Volume 23 Issue 3-4 | Foundations and Trends in Communications and Information Theory | Emerald Publishing 2026-05-19T15:46:33+00:00 https://doi.org/10.1108/FTCIT-09-2025-0149 cshalizi to_read information_theory learning_theory learning_under_dependence in_NB low-regret_learning online_learning https://pinboard.in/ https://pinboard.in/u:cshalizi/b:eb2f88390f74/ [2604.19560] Separating Geometry from Probability in the Analysis of Generalization 2026-04-22T20:22:34+00:00 https://arxiv.org/abs/2604.19560 cshalizi to:NB to_read recht.benjamin raginsky.maxim learning_theory optimization via:mraginsky to_teach:childs_garden_of_statistical_learning_theory straight_into_my_veins interpolation https://pinboard.in/ https://pinboard.in/u:cshalizi/b:963cc7aaa897/ On the rate of convergence of an over-parametrized deep neural network regression estimate with ReLU activation function learned by gradient descent 2025-10-24T19:40:42+00:00 https://projecteuclid.org/journals/electronic-journal-of-statistics/volume-19/issue-2/On-the-rate-of-convergence-of-an-over-parametrized-deep/10.1214/25-EJS2444.full cshalizi to:NB regression neural_networks learning_theory nonparametrics https://pinboard.in/ https://pinboard.in/u:cshalizi/b:deab690bc7f0/ Statistical learning for $$psi $$ -weakly dependent processes | Statistical Inference for Stochastic Processes 2025-09-03T14:22:34+00:00 https://link.springer.com/article/10.1007/s11203-025-09329-6 cshalizi to:NB learning_theory mixing time_series https://pinboard.in/ https://pinboard.in/u:cshalizi/b:47b97e670aaa/ [2505.00110] On the expressivity of deep Heaviside networks 2025-08-07T14:56:37+00:00 https://arxiv.org/abs/2505.00110 cshalizi to:NB neural_networks learning_theory https://pinboard.in/ https://pinboard.in/u:cshalizi/b:ed098f79a41e/ On the Vapnik-Chervonenkis dimension of computer programs which use transcendental elementary operations | Annals of Mathematics and Artificial Intelligence 2025-04-23T14:38:17+00:00 https://link.springer.com/article/10.1007/s10472-009-9148-3 cshalizi to:NB learning_theory computational_complexity via:mraginsky https://pinboard.in/ https://pinboard.in/u:cshalizi/b:eeec04e7e149/ A U-turn on Double Descent: Rethinking Parameter Counting in Statistical Learning | OpenReview 2025-04-01T20:46:09+00:00 https://openreview.net/forum?id=O0Lz8XZT2b cshalizi learning_theory regression interpolation_aka_memorizing_the_training_data to_teach:childs_garden_of_statistical_learning_theory via:rvenkat in_NB have_read https://pinboard.in/ https://pinboard.in/u:cshalizi/b:5c9e184baef1/ The Uses and Limitations of Occam Algorithms: a response to Herrmann - PhilSci-Archive 2025-03-26T15:22:08+00:00 https://philsci-archive.pitt.edu/24910/ cshalizi learning_theory occams_razor have_read in_NB https://pinboard.in/ https://pinboard.in/u:cshalizi/b:518cdda4fc1c/ now publishers - Generalization Bounds: Perspectives from Information Theory and PAC-Bayes 2025-03-20T13:04:53+00:00 https://www.nowpublishers.com/article/Details/MAL-112 cshalizi to:NB downloaded books:noted to_read learning_theory information_theory raginsky.maxim to_teach:childs_garden_of_statistical_learning_theory https://pinboard.in/ https://pinboard.in/u:cshalizi/b:72659330abf1/ [2503.02113] Deep Learning is Not So Mysterious or Different 2025-03-16T19:30:19+00:00 https://arxiv.org/abs/2503.02113 cshalizi to:NB to_read neural_networks learning_theory to_teach:childs_garden_of_statistical_learning_theory to_teach:statistics_and_generative_ai https://pinboard.in/ https://pinboard.in/u:cshalizi/b:7dc2f4d6c2dd/ [2502.20375] When does a predictor know its own loss? 2025-03-01T16:42:13+00:00 https://arxiv.org/abs/2502.20375 cshalizi to:NB prediction learning_theory via:mraginsky https://pinboard.in/ https://pinboard.in/u:cshalizi/b:f05f155b04ee/ [2411.00247] Deep Learning Through A Telescoping Lens: A Simple Model Provides Empirical Insights On Grokking, Gradient Boosting & Beyond 2025-01-22T15:36:23+00:00 https://arxiv.org/abs/2411.00247 cshalizi to:NB neural_networks learning_theory statistics to_read via:mraginsky to_teach:statistics_and_generative_ai https://pinboard.in/ https://pinboard.in/u:cshalizi/b:b500158ab0cc/ [2412.07684] The Pitfalls of Memorization: When Memorization Hurts Generalization 2025-01-01T15:54:07+00:00 https://arxiv.org/abs/2412.07684 cshalizi in_NB learning_theory interpolation_aka_memorizing_the_training_data https://pinboard.in/ https://pinboard.in/u:cshalizi/b:9759291e2c99/ Learning Theory from First Principles (Bach, forthcoming [2024]) 2024-12-11T16:37:03+00:00 https://www.di.ens.fr/~fbach/ltfp_book.pdf cshalizi to:NB books:noted downloaded learning_theory bach.francis https://pinboard.in/ https://pinboard.in/u:cshalizi/b:5930b85a3c93/ [2410.10101] Learning Linear Attention in Polynomial Time 2024-12-11T16:35:24+00:00 https://arxiv.org/abs/2410.10101 cshalizi to:NB learning_theory large_language_models_(so_called) https://pinboard.in/ https://pinboard.in/u:cshalizi/b:632ce3a0b3f9/ Alexey Chervonenkis's Bibliography: Introductory Comments 2024-12-11T16:00:42+00:00 https://www.jmlr.org/papers/v16/gammerman15b.html cshalizi to:NB to_read learning_theory history_of_science via:mraginsky re:paradigm_formation_in_statistical_learning https://pinboard.in/ https://pinboard.in/u:cshalizi/b:5f41bff80bdd/ [2411.00109] Prospective Learning: Learning for a Dynamic Future 2024-11-07T15:10:53+00:00 https://arxiv.org/abs/2411.00109 cshalizi in_NB learning_theory learning_under_dependence https://pinboard.in/ https://pinboard.in/u:cshalizi/b:9aae6e7c7f2f/ [2304.06670] Do deep neural networks have an inbuilt Occam's razor? 2024-10-08T22:55:19+00:00 https://arxiv.org/abs/2304.06670 cshalizi via:vaguery learning_theory neural_networks bayesianism to_read https://pinboard.in/ https://pinboard.in/u:cshalizi/b:f2d4bd730be9/ [2407.20199] Emergence in non-neural models: grokking modular arithmetic via average gradient outer product 2024-09-19T20:01:34+00:00 https://arxiv.org/abs/2407.20199 cshalizi to:NB learning_theory https://pinboard.in/ https://pinboard.in/u:cshalizi/b:1e37f2ea52ac/ Grokking Beyond Neural Networks: An Empirical Exploration with Model Complexity | OpenReview 2024-09-19T20:00:20+00:00 https://openreview.net/forum?id=ux9BrxPCl8 cshalizi to:NB learning_theory https://pinboard.in/ https://pinboard.in/u:cshalizi/b:594e324479e0/ [2401.14483] Four Facets of Forecast Felicity: Calibration, Predictiveness, Randomness and Regret 2024-09-17T17:59:19+00:00 https://arxiv.org/abs/2401.14483 cshalizi to:NB to_read prediction game_theory learning_theory low-regret_learning calibration https://pinboard.in/ https://pinboard.in/u:cshalizi/b:fca0556a77fc/ [2310.20360] Mathematical Introduction to Deep Learning: Methods, Implementations, and Theory 2024-09-05T13:41:00+00:00 https://arxiv.org/abs/2310.20360 cshalizi neural_networks learning_theory books:noted in_NB https://pinboard.in/ https://pinboard.in/u:cshalizi/b:bdf0ef9b6702/ [2202.06915] Stochastic linear optimization never overfits with quadratically-bounded losses on general data 2024-07-17T15:26:49+00:00 https://arxiv.org/abs/2202.06915 cshalizi in_NB learning_theory optimization telgarsky.matus https://pinboard.in/ https://pinboard.in/u:cshalizi/b:f16b1331c21a/ [2404.03774] Exploration is Harder than Prediction: Cryptographically Separating Reinforcement Learning from Supervised Learning 2024-07-17T14:53:47+00:00 https://arxiv.org/abs/2404.03774 cshalizi in_NB learning_theory reinforcement_learning computational_complexity https://pinboard.in/ https://pinboard.in/u:cshalizi/b:2962e58071e6/ [2404.06757] Language Generation in the Limit 2024-07-17T14:42:52+00:00 https://arxiv.org/abs/2404.06757 cshalizi in_NB formal_languages learning_theory grammar_induction kleinberg.jon to_read https://pinboard.in/ https://pinboard.in/u:cshalizi/b:064dd4cafd1e/ [2405.18055v1] Dimension-free uniform concentration bound for logistic regression 2024-06-10T14:16:59+00:00 https://arxiv.org/abs/2405.18055v1 cshalizi to:NB to_read logistic_regression learning_theory to_teach:childs_garden_of_statistical_learning_theory via:? https://pinboard.in/ https://pinboard.in/u:cshalizi/b:2fb188076270/ [2402.14987] On the Performance of Empirical Risk Minimization with Smoothed Data 2024-03-05T16:33:38+00:00 https://arxiv.org/abs/2402.14987 cshalizi learning_theory rakhlin.alexander optimization in_NB https://pinboard.in/ https://pinboard.in/u:cshalizi/b:59e6353bf8b8/ Minimax rates for conditional density estimation via empirical entropy 2024-03-05T14:57:19+00:00 https://projecteuclid.org/journals/annals-of-statistics/volume-51/issue-2/Minimax-rates-for-conditional-density-estimation-via-empirical-entropy/10.1214/23-AOS2270.short cshalizi in_NB density_estimation learning_theory via:mraginsky https://pinboard.in/ https://pinboard.in/u:cshalizi/b:0416eeb58e24/ [2110.11216] User-friendly introduction to PAC-Bayes bounds 2024-03-02T19:25:18+00:00 https://arxiv.org/abs/2110.11216 cshalizi to:NB to_read learning_theory ensemble_methods to_teach:childs_garden_of_statistical_learning_theory alquier.pierre https://pinboard.in/ https://pinboard.in/u:cshalizi/b:27997bd5aeb9/ [2402.13285] Leveraging PAC-Bayes Theory and Gibbs Distributions for Generalization Bounds with Complexity Measures 2024-02-27T20:03:04+00:00 https://arxiv.org/abs/2402.13285 cshalizi to:NB learning_theory https://pinboard.in/ https://pinboard.in/u:cshalizi/b:2031e4da5d2d/ [2402.01502] Why do Random Forests Work? Understanding Tree Ensembles as Self-Regularizing Adaptive Smoothers 2024-02-27T19:59:40+00:00 https://arxiv.org/abs/2402.01502 cshalizi to_read ensemble_methods random_forests decision_trees learning_theory in_NB https://pinboard.in/ https://pinboard.in/u:cshalizi/b:afc37c93e049/ [2311.07013] A PAC-Bayesian Perspective on the Interpolating Information Criterion 2024-02-15T18:33:43+00:00 https://arxiv.org/abs/2311.07013 cshalizi information_criteria learning_theory mahoney.michael_w. in_NB interpolation_aka_memorizing_the_training_data https://pinboard.in/ https://pinboard.in/u:cshalizi/b:b054db187920/ [2109.02224] On Empirical Risk Minimization with Dependent and Heavy-Tailed Data 2023-12-14T11:31:16+00:00 https://arxiv.org/abs/2109.02224 cshalizi to:NB to_read learning_theory mixing heavy_tails learning_under_dependence https://pinboard.in/ https://pinboard.in/u:cshalizi/b:9123f4f94745/ [2309.13786] Distribution-Free Statistical Dispersion Control for Societal Applications 2023-12-09T01:22:25+00:00 https://arxiv.org/abs/2309.13786 cshalizi to:NB learning_theory https://pinboard.in/ https://pinboard.in/u:cshalizi/b:ff6def22a22f/ [2305.18887] How Does Information Bottleneck Help Deep Learning? 2023-12-09T01:20:24+00:00 https://arxiv.org/abs/2305.18887 cshalizi to:NB information_bottleneck neural_networks learning_theory to_teach:statistics_and_generative_ai https://pinboard.in/ https://pinboard.in/u:cshalizi/b:61af1aefcaa9/ [2311.03910] Structure of universal formulas 2023-12-08T19:04:39+00:00 https://arxiv.org/abs/2311.03910 cshalizi to:NB learning_theory neural_networks approximation https://pinboard.in/ https://pinboard.in/u:cshalizi/b:43e65eb23777/ [2309.17016] Efficient Agnostic Learning with Average Smoothness 2023-12-08T17:15:57+00:00 https://arxiv.org/abs/2309.17016 cshalizi in_NB nonparametrics learning_theory empirical_processes kith_and_kin kontorovich.aryeh hanneke.steve https://pinboard.in/ https://pinboard.in/u:cshalizi/b:372bb023a730/ [2305.11042] A unified framework for information-theoretic generalization bounds 2023-09-29T15:59:52+00:00 https://arxiv.org/abs/2305.11042 cshalizi in_NB learning_theory information_theory raginsky.maxim https://pinboard.in/ https://pinboard.in/u:cshalizi/b:89c7fa1175e6/ [1202.3699] Learning is planning: near Bayes-optimal reinforcement learning via Monte-Carlo tree search 2023-08-14T17:45:19+00:00 https://arxiv.org/abs/1202.3699 cshalizi in_NB reinforcement_learning learning_theory littman.michael_l. via:? https://pinboard.in/ https://pinboard.in/u:cshalizi/b:db4b86ee8a65/ [2007.13982] Distributionally Robust Losses for Latent Covariate Mixtures 2023-07-31T01:35:05+00:00 https://arxiv.org/abs/2007.13982 cshalizi to_read learning_theory re:codename:one_law_for_the_lion_and_ox_is_oppression algorithmic_fairness duchi.john via:rvenkat scooped? in_NB https://pinboard.in/ https://pinboard.in/u:cshalizi/b:e92126446535/ [2210.03458] PAC Privacy: Automatic Privacy Measurement and Control of Data Processing 2023-07-18T18:50:44+00:00 https://arxiv.org/abs/2210.03458 cshalizi to:NB learning_theory privacy https://pinboard.in/ https://pinboard.in/u:cshalizi/b:1bedb5604493/ [2202.09889] Memorize to Generalize: on the Necessity of Interpolation in High Dimensional Linear Regression 2023-06-28T16:12:30+00:00 https://arxiv.org/abs/2202.09889 cshaliziin_NB learning_theory interpolation_aka_memorizing_the_training_data https://pinboard.in/ https://pinboard.in/u:cshalizi/b:b1a70c7be3e0/ A plug-in uniform law of large numbers - Biased and Inefficient 2023-06-15T19:18:32+00:00 https://notstatschat.rbind.io/2022/09/28/uniform-law-of-large-numbers/ cshalizihave_read ergodic_theory empirical_processes lumley.thomas learning_theory re:HEAS in_NB https://pinboard.in/ https://pinboard.in/u:cshalizi/b:1dfcf0d1d3f9/ [2305.17592] Approximation-Generalization Trade-offs under (Approximate) Group Equivariance 2023-06-05T02:40:59+00:00 https://arxiv.org/abs/2305.17592 cshalizi symmetry learning_theory in_NB have_read https://pinboard.in/ https://pinboard.in/u:cshalizi/b:7639b9f8db7b/ Learning probabilistic prediction functions | IEEE Conference Publication | IEEE Xplore 2023-05-08T19:22:57+00:00 https://ieeexplore.ieee.org/document/21929 cshalizi in_NB learning_theory prediction have_read low-regret_learning probability cleaning_out_the_filing_cabinet_for_the_first_time_since_2005 https://pinboard.in/ https://pinboard.in/u:cshalizi/b:19a5b745c5e5/ Efficient unsupervised learning | Proceedings of the first annual workshop on Computational learning theory 2023-05-08T19:16:48+00:00 https://dl.acm.org/doi/abs/10.5555/93025.93105 cshalizito:NB learning_theory cleaning_out_the_filing_cabinet_for_the_first_time_since_2005 have_read https://pinboard.in/ https://pinboard.in/u:cshalizi/b:23bb7536d7ad/ [2305.00322] Toward $L_infty$-recovery of Nonlinear Functions: A Polynomial Sample Complexity Bound for Gaussian Random Fields 2023-05-05T01:47:16+00:00 https://arxiv.org/abs/2305.00322 cshalizi approximation learning_theory random_fields in_NB https://pinboard.in/ https://pinboard.in/u:cshalizi/b:fb73aea45ac1/ Random Features Model with General Convex Regularization: A Fine Grained Analysis with Precise Asymptotic Learning Curves 2023-04-27T14:42:18+00:00 https://proceedings.mlr.press/v206/bosch23a cshalizi random_features learning_theory to_read in_NB https://pinboard.in/ https://pinboard.in/u:cshalizi/b:f67c431b3165/ [2107.04562] The Bayesian Learning Rule 2023-03-18T14:30:57+00:00 https://arxiv.org/abs/2107.04562 cshalizi to:NB learning_theory optimization bayesianism color_me_skeptical have_skimmed https://pinboard.in/ https://pinboard.in/u:cshalizi/b:928b90fa32e5/ [2303.05369] Data-dependent Generalization Bounds via Variable-Size Compressibility 2023-03-18T13:51:32+00:00 https://arxiv.org/abs/2303.05369 cshalizi information_theory learning_theory to_read in_NB https://pinboard.in/ https://pinboard.in/u:cshalizi/b:09b32ab25cd5/ [2302.06005] Near-optimal learning with average Hölder smoothness 2023-02-24T03:27:08+00:00 https://arxiv.org/abs/2302.06005 cshalizi to:NB learning_theory nonparametrics kontorovich.aryeh hanneke.steve https://pinboard.in/ https://pinboard.in/u:cshalizi/b:3454a701b130/ [2302.07263] Interpolation Learning With Minimum Description Length 2023-02-24T03:25:19+00:00 https://arxiv.org/abs/2302.07263 cshalizi mdl learning_theory in_NB interpolation_aka_memorizing_the_training_data https://pinboard.in/ https://pinboard.in/u:cshalizi/b:910225f7e41f/ [2212.13556] Limitations of Information-Theoretic Generalization Bounds for Gradient Descent Methods in Stochastic Convex Optimization 2023-01-18T03:11:36+00:00 https://arxiv.org/abs/2212.13556 cshalizi to:NB optimization information_theory learning_theory minimax https://pinboard.in/ https://pinboard.in/u:cshalizi/b:c922f5bb9181/ On Learnability Under General Stochastic Processes · Issue 4.4, Fall 2022 2022-12-09T20:08:14+00:00 https://hdsr.mitpress.mit.edu/pub/qixx99zn/release/1 cshalizi to:NB learning_theory online_learning low-regret_learning to_read tewari.ambuj learning_under_dependence dawid.a._philip stochastic_processes to_teach:childs_garden_of_statistical_learning_theory https://pinboard.in/ https://pinboard.in/u:cshalizi/b:d8309e159972/ [2105.12806] A Universal Law of Robustness via Isoperimetry 2022-11-14T15:14:12+00:00 https://arxiv.org/abs/2105.12806 cshalizi learning_theory bubeck.sebastien in_NB interpolation_aka_memorizing_the_training_data https://pinboard.in/ https://pinboard.in/u:cshalizi/b:5f42a23ae835/ [2202.04985] Generalization Bounds via Convex Analysis 2022-08-25T16:12:32+00:00 https://arxiv.org/abs/2202.04985 cshalizi to:NB learning_theory information_theory convexity to_teach:childs_garden_of_statistical_learning_theory https://pinboard.in/ https://pinboard.in/u:cshalizi/b:113aa8fd4ed1/ [2204.01119] Fitting an immersed submanifold to data via Sussmann's orbit theorem 2022-08-04T14:50:37+00:00 https://arxiv.org/abs/2204.01119 cshalizi to:NB to_read re:codename:catherine_wheel manifold_learning learning_theory raginsky.maxim https://pinboard.in/ https://pinboard.in/u:cshalizi/b:21a9eb190fb7/ [2112.03626] Phase transitions in nonparametric regressions: a curse of exploiting higher degree smoothness assumptions in finite samples 2022-07-25T17:15:55+00:00 https://arxiv.org/abs/2112.03626 cshalizi in_NB regression nonparametrics minimax learning_theory statistics https://pinboard.in/ https://pinboard.in/u:cshalizi/b:e1ba3a57ef77/ Data-Derived Weak Universal Consistency 2022-07-19T13:56:11+00:00 https://jmlr.org/papers/v23/20-644.html cshalizi in_NB learning_theory statistics information_theory to_read to_teach:childs_garden_of_statistical_learning_theory https://pinboard.in/ https://pinboard.in/u:cshalizi/b:7ba350217b53/ [2202.04415] Towards Empirical Process Theory for Vector-Valued Functions: Metric Entropy of Smooth Function Classes 2022-06-13T17:00:24+00:00 https://arxiv.org/abs/2202.04415 cshalizi to:NB learning_theory empirical_processes hilbert_space via:? https://pinboard.in/ https://pinboard.in/u:cshalizi/b:fe711e83cc23/ [2206.03515] How does overparametrization affect performance on minority groups? 2022-06-09T08:51:42+00:00 https://arxiv.org/abs/2206.03515 cshalizi to:NB learning_theory random_features algorithmic_fairness re:codename:one_law_for_the_lion_and_ox_is_oppression https://pinboard.in/ https://pinboard.in/u:cshalizi/b:bac4cf470627/ [2205.01593] Causal Regularization: On the trade-off between in-sample risk and out-of-sample risk guarantees 2022-05-11T16:49:40+00:00 https://arxiv.org/abs/2205.01593 cshalizi to:NB causal_inference learning_theory prediction https://pinboard.in/ https://pinboard.in/u:cshalizi/b:b92b191c8fa9/ Phys. Rev. Research 4, 013201 (2022) - Memorizing without overfitting: Bias, variance, and interpolation in overparameterized models 2022-05-10T13:14:41+00:00 https://journals.aps.org/prresearch/abstract/10.1103/PhysRevResearch.4.013201 cshalizi learning_theory linear_regression neural_networks via:rvenkat in_NB random_features of_course_its_really_a_spin_glass interpolation_aka_memorizing_the_training_data have_read https://pinboard.in/ https://pinboard.in/u:cshalizi/b:8af8a18b4806/ [2103.14108] The Geometry of Over-parameterized Regression and Adversarial Perturbations 2022-05-10T13:13:10+00:00 https://arxiv.org/abs/2103.14108 cshalizi to:NB linear_regression neural_networks learning_theory your_favorite_deep_neural_network_sucks via:rvenkat adversarial_examples https://pinboard.in/ https://pinboard.in/u:cshalizi/b:af2e2e202d0c/ [2204.02909v1] A Short Tutorial on Mean-Field Spin Glass Techniques for Non-Physicists 2022-04-25T13:27:49+00:00 https://arxiv.org/abs/2204.02909v1 cshalizi to_read spin_glasses statistical_mechanics learning_theory high-dimensional_statistics montanari.andrea via:rvenkat in_NB https://pinboard.in/ https://pinboard.in/u:cshalizi/b:2b39f37fa8bf/ Data-Derived Weak Universal Consistency 2022-03-27T15:54:29+00:00 https://www.jmlr.org/papers/v23/20-644.html cshalizi to:NB learning_theory information_theory to_read https://pinboard.in/ https://pinboard.in/u:cshalizi/b:c0172f9b465c/ Choosing among Regularized Estimators in Empirical Economics: The Risk of Machine Learning | The Review of Economics and Statistics | MIT Press 2022-03-14T18:19:21+00:00 https://direct.mit.edu/rest/article-abstract/101/5/743/58556/Choosing-among-Regularized-Estimators-in-Empirical?redirectedFrom=fulltext cshalizi to:NB econometrics estimation statistics learning_theory to_teach:childs_garden_of_statistical_learning_theory re:HEAS downloaded cross-validation https://pinboard.in/ https://pinboard.in/u:cshalizi/b:765356ad4562/ [2201.10408] Beyond the Frontier: Fairness Without Accuracy Loss 2022-03-14T18:12:52+00:00 https://arxiv.org/abs/2201.10408 cshalizi algorithmic_fairness learning_theory roth.aaron to_teach:data-mining kearns.michael in_NB blogged https://pinboard.in/ https://pinboard.in/u:cshalizi/b:a6689f803747/ On Optimal Learning With Random Features | IEEE Journals & Magazine | IEEE Xplore 2022-03-08T14:46:23+00:00 https://ieeexplore.ieee.org/abstract/document/9724643 cshalizi to:NB hilbert_space learning_theory random_features https://pinboard.in/ https://pinboard.in/u:cshalizi/b:99f1a282aa31/