Learning Theory

Data Contamination: From Memorization to Exploitation ACL 2022 Data-Derived Weak Universal Consistency JMLR 2022 Data Scaling Laws in NMT: The Effect of Noise and Architecture ICML 2022 DAVINZ: Data Valuation using Deep Neural Networks at Initialization ICML 2022 Debiasing Samples from Online Learning Using Bootstrap AISTATS 2022 Deciphering Lasso-based Classification Through a Large Dimensional Analysis of the Iterative Soft-Thresholding Algorithm ICML 2022 Decision-Focused Learning without Decision-Making: Learning Locally Optimized Decision Losses NeurIPS 2022 Decomposable Non-Smooth Convex Optimization with Nearly-Linear Gradient Oracle Complexity NeurIPS 2022 Deep Architecture Connectivity Matters for Its Convergence: A Fine-Grained Analysis NeurIPS 2022 Deep Learning with Logical Constraints IJCAI 2022 Deep Limits and a Cut-Off Phenomenon for Neural Networks JMLR 2022 Deep Networks on Toroids: Removing Symmetries Reveals the Structure of Flat Regions in the Landscape Geometry ICML 2022 Demystifying the Neural Tangent Kernel From a Practical Perspective: Can It Be Trusted for Neural Architecture Search Without Training? CVPR 2022 Depth and Feature Learning are Provably Beneficial for Neural Network Discriminators COLT 2022 Depth is More Powerful than Width with Prediction Concatenation in Deep Forest NeurIPS 2022 Depth separation beyond radial functions JMLR 2022 Differentially Private Learning with Margin Guarantees NeurIPS 2022 Distinguishing Learning Rules with Brain Machine Interfaces NeurIPS 2022 Distinguishing Relational Pattern Languages With a Small Number of Short Strings ALT 2022 Distinguishing rule and exemplar-based generalization in learning systems ICML 2022 Diversity and Generalization in Neural Network Ensembles AISTATS 2022 Does BERT Know that the IS-A Relation Is Transitive? ACL 2022 Does BERT really agree ? Fine-grained Analysis of Lexical Dependence on a Syntactic Task ACL 2022 Does Momentum Change the Implicit Regularization on Separable Data? NeurIPS 2022 Does the Data Induce Capacity Control in Deep Learning? ICML 2022