January 15, 2019 article Open access Gradient Descent with Identity Initialization Efficiently Learns Positive-Definite Linear Transformations by Deep Residual Networks Neural Computation DOI: 10.1162/neco_a_01164 Full text (OA) OpenAlex Authors 0 Author list not loaded yet. Cited by 2 stored of 48 Search Sort Most cited Newest Oldest Patent citations Title Any typearticle review book-chapter conference-paper preprint dissertation book dataset other Any fieldAgricultural and Biological Sciences Arts and Humanities Biochemistry, Genetics and Molecular Biology Business, Management and Accounting Chemical Engineering Chemistry Computer Science Decision Sciences Dentistry Earth and Planetary Sciences Economics, Econometrics and Finance Energy Engineering Environmental Science Health Professions Immunology and Microbiology Materials Science Mathematics Medicine Neuroscience Nursing Pharmacology, Toxicology and Pharmaceutics Physics and Astronomy Psychology Social Sciences Veterinary Open access Gradient Descent for Deep Matrix Factorization: Dynamics and Implicit Bias Towards Low Rank 2022 SSRN Electronic Journal preprint Computer Science Stochastic Gradient Optimization Techniques Open access 5 citations The loss landscape of deep linear neural networks: a second-order analysis 2021 arXiv (Cornell University) preprint Computer Science Stochastic Gradient Optimization Techniques Open access 1 citations 2 results References 0