Learning Theory

Towards Understanding Knowledge Distillation ICML 2019 Towards Understanding the Generalization Bias of Two Layer Convolutional Linear Classifiers with Gradient Descent AISTATS 2019 Train and Test Tightness of LP Relaxations in Structured Prediction JMLR 2019 Transfer Learning via Minimizing the Performance Gap Between Domains NeurIPS 2019 Triad Constraints for Learning Causal Structure of Latent Variables NeurIPS 2019 Understanding and Visualizing Raw Waveform-Based CNNs Interspeech 2019 Understanding Data Augmentation in Neural Machine Translation: Two Perspectives towards Generalization EMNLP 2019 Understanding Priors in Bayesian Neural Networks at the Unit Level ICML 2019 Uniform concentration and symmetrization for weak interactions COLT 2019 Uniform convergence may be unable to explain generalization in deep learning NeurIPS 2019 Unifying the Stochastic and the Adversarial Bandits with Knapsack IJCAI 2019 Universality of Computational Lower Bounds for Submatrix Detection COLT 2019 Universal Statistics of Fisher Information in Deep Neural Networks: Mean Field Approach AISTATS 2019 Unsupervised Domain Adaptation Based on Source-Guided Discrepancy AAAI 2019 Updates of Equilibrium Prop Match Gradients of Backprop Through Time in an RNN with Static Input NeurIPS 2019 Using Benson’s Algorithm for Regularization Parameter Tracking AAAI 2019 Variational Regret Bounds for Reinforcement Learning UAI 2019 VC Classes are Adversarially Robustly Learnable, but Only Improperly COLT 2019 Weighted Abstract Dialectical Frameworks through the Lens of Approximation Fixpoint Theory AAAI 2019 What Can ResNet Learn Efficiently, Going Beyond Kernels? NeurIPS 2019 What Does It Mean to Learn in Deep Networks? And, How Does One Detect Adversarial Attacks? CVPR 2019 What Is One Grain of Sand in the Desert? Analyzing Individual Neurons in Deep NLP Models AAAI 2019 Which Factorization Machine Modeling Is Better: A Theoretical Answer with Optimal Guarantee AAAI 2019 Why do Larger Models Generalize Better? A Theoretical Perspective via the XOR Problem ICML 2019 Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent NeurIPS 2019