{"version":1,"pages":[{"id":"-MEnQiHwoDwQ0WlBXj1P","title":"PAPER NOTES","pathname":"/paper_notes","siteSpaceId":"sitesp_ySQ2C","description":"This folder is used to archive paper notes."},{"id":"-MEyilMdtZqcwj_1Asb5","title":"Meta-Learning with Implicit Gradient","pathname":"/paper_notes/meta-learning-with-implicit-gradient","siteSpaceId":"sitesp_ySQ2C","description":"NIPS 2019"},{"id":"-MF3ioISS2LMvSZin5xi","title":"DARTS: Differentiable Architecture Search","pathname":"/paper_notes/darts-differentiable-architecture-search","siteSpaceId":"sitesp_ySQ2C","description":"ICLR 2019             8/19/2020"},{"id":"-MFBO8WCGYSADualFv6_","title":"Meta-Learning of Neural Architectures for Few-Shot Learning","pathname":"/paper_notes/meta-learning-of-neural-architectures-for-few-shot-learning","siteSpaceId":"sitesp_ySQ2C","description":"CVPR 2020     8-22-2020"},{"id":"-MFMuZM7ftjQEh2xZ3j2","title":"Towards Fast Adaptation of Neural Architectures with Meta Learning","pathname":"/paper_notes/towards-fast-adaptation-of-neural-architectures-with-meta-learning","siteSpaceId":"sitesp_ySQ2C","description":""},{"id":"-MFOUASPHL0JM6hyazFc","title":"Editable Neural Networks","pathname":"/paper_notes/editable-neural-networks","siteSpaceId":"sitesp_ySQ2C","description":"ICLR 2020    8-22-2020"},{"id":"-MFOSLwqkxb3_SNScgOE","title":"ANIL (Almost No Inner Loop)","pathname":"/paper_notes/anil","siteSpaceId":"sitesp_ySQ2C","description":"ICLR 2020      8-23-2020"},{"id":"-MFWHAM6GUotTmInMZpX","title":"Meta-Learning Representation for Continual Learning","pathname":"/paper_notes/meta-learning-representation-for-continual-learning","siteSpaceId":"sitesp_ySQ2C","description":"NeurIPS 2019            8-24-2020"},{"id":"-MFWI9YlsrxjWV8oGNPZ","title":"Learning to learn by gradient descent by gradient descent","pathname":"/paper_notes/learning-to-learn-by-gradient-descent-by-gradient-descent","siteSpaceId":"sitesp_ySQ2C","description":"NIPS 2016     8-24-2020"},{"id":"-MFWIOgznQj8wLYhkJS8","title":"Modular Meta-Learning with Shrinkage","pathname":"/paper_notes/modular-meta-learning-with-shrinkage","siteSpaceId":"sitesp_ySQ2C","description":"8-24-2020"},{"id":"-MFncBeJOTSZnzkfBksD","title":"NADS: Neural Architecture Distribution Search for Uncertainty Awareness","pathname":"/paper_notes/nads-neural-architecture-distribution-search-for-uncertainty-awarenessrandy","siteSpaceId":"sitesp_ySQ2C","description":"ICML 2020         08-28-2020"},{"id":"-MFnd7V_Ud4DipQ1zdpo","title":"Modular Meta Learning","pathname":"/paper_notes/modular-meta-learning","siteSpaceId":"sitesp_ySQ2C","description":"CoRL 2018"},{"id":"-MGd8xYVtSTtMrsdJ3c5","title":"Incremental Few Shot Learning with Attention Attractor Network","pathname":"/paper_notes/sep/incremental-few-shot-learning-with-attention-attractor-network","siteSpaceId":"sitesp_ySQ2C","description":"NeurIPS 2019           9/7/2020","breadcrumbs":[{"label":"Sep"}]},{"id":"-MHHR3OgAItd4rCI34tm","title":"Learning Steady-States of Iterative Algorithms over Graphs","pathname":"/paper_notes/sep/learning-steady-states-of-iterative-algorithms-over-graphs","siteSpaceId":"sitesp_ySQ2C","description":"ICML 2018                  9/15/2020","breadcrumbs":[{"label":"Sep"}]},{"id":"-MHIGQTS3DwOwCvpx52Q","title":"Experiments","pathname":"/paper_notes/sep/learning-steady-states-of-iterative-algorithms-over-graphs/experiments","siteSpaceId":"sitesp_ySQ2C","description":"","breadcrumbs":[{"label":"Sep"},{"label":"Learning Steady-States of Iterative Algorithms over Graphs"}]},{"id":"-MHsxrZGMolQNNtpzJE1","title":"Learning combinatorial optimization algorithms over graphs","pathname":"/paper_notes/sep/learning-combinatorial-optimization-algorithms-over-graphs","siteSpaceId":"sitesp_ySQ2C","description":"NIPS 2017    9-22-2020","breadcrumbs":[{"label":"Sep"}]},{"id":"-MG4OMmXnQtwS_Xp3R-5","title":"Meta-Learning with Shared Amortized Variational Inference","pathname":"/paper_notes/sep/meta-learning-with-shared-amortized-variational-inference","siteSpaceId":"sitesp_ySQ2C","description":"(ICML 2020)","breadcrumbs":[{"label":"Sep"}]},{"id":"-MG4Om53OG_bfFT39JrP","title":"Concept Learners for Generalizable Few-Shot Learning","pathname":"/paper_notes/sep/concept-learners-for-generalizable-few-shotlearning","siteSpaceId":"sitesp_ySQ2C","description":"","breadcrumbs":[{"label":"Sep"}]},{"id":"-MG4PCBmS-bOOFbfJm4v","title":"Progressive Graph Learning for Open-Set Domain Adaptation","pathname":"/paper_notes/sep/progressive-graph-learning-for-open-set-domain-adaptation","siteSpaceId":"sitesp_ySQ2C","description":"","breadcrumbs":[{"label":"Sep"}]},{"id":"-MHRpoWvOPyWMIktpg43","title":"Probabilistic Neural Architecture Search","pathname":"/paper_notes/sep/probabilistic-neural-architecture-search","siteSpaceId":"sitesp_ySQ2C","description":"","breadcrumbs":[{"label":"Sep"}]},{"id":"-MI4rc4Wa9tlNro6xhOc","title":"Large-Scale Long-Tailed Recognition in an Open World","pathname":"/paper_notes/sep/large-scale-long-tailed-recognition-in-an-open-world","siteSpaceId":"sitesp_ySQ2C","description":"9-25-2020","breadcrumbs":[{"label":"Sep"}]},{"id":"-MI4s8mHa2pO_HD7j9z5","title":"Learning to stop while learning to predict","pathname":"/paper_notes/sep/learning-to-stop-while-learning-to-predict","siteSpaceId":"sitesp_ySQ2C","description":"ICML2020   9-25-2020","breadcrumbs":[{"label":"Sep"}]},{"id":"-MIN-eIPGVRmUYOokJVH","title":"Adaptive Risk Minimization: A Meta-Learning Approach for Tackling Group Shift","pathname":"/paper_notes/sep/adaptive-risk-minimization-a-meta-learning-approach-for-tackling-group-shift","siteSpaceId":"sitesp_ySQ2C","description":"9-28-2020","breadcrumbs":[{"label":"Sep"}]},{"id":"-MIN0QFoaOMo18cuFf6W","title":"Learning to Generalize: Meta-Learning for Domain Generalization","pathname":"/paper_notes/sep/learning-to-generalize-meta-learning-for-domain-generalization","siteSpaceId":"sitesp_ySQ2C","description":"AAAI-18    9-28-2020","breadcrumbs":[{"label":"Sep"}]},{"id":"-MG5GYv25k6ZNPPIjBrc","title":"Meta-Learning Acquisition Functions for Transfer Learning in Bayesian Optimization","pathname":"/paper_notes/oct/meta-learning-acquisition-functions-for-transfer-learning-in-bayesian-optimization","siteSpaceId":"sitesp_ySQ2C","description":"ICLR 20  10-2-2020","breadcrumbs":[{"label":"Oct"}]},{"id":"-MKXlu64TwIyjK_krSMS","title":"Network Architecture Search for Domain Adaptation","pathname":"/paper_notes/oct/network-architecture-search-for-domain-adaptation","siteSpaceId":"sitesp_ySQ2C","description":"arxiv  10-2-2020","breadcrumbs":[{"label":"Oct"}]},{"id":"-MKXmIJ4NZJgtjqGCPmE","title":"Continuous Meta Learning without tasks","pathname":"/paper_notes/oct/continuous-meta-learning-without-tasks","siteSpaceId":"sitesp_ySQ2C","description":"NeurIPS 20       10-9-2020","breadcrumbs":[{"label":"Oct"}]},{"id":"-MKXmvu_0VPrCB3ST9PN","title":"Learning Causal Models Online","pathname":"/paper_notes/oct/learning-causal-models-online","siteSpaceId":"sitesp_ySQ2C","description":"arxiv   10-9-2020","breadcrumbs":[{"label":"Oct"}]},{"id":"-MKXnHyTCVwTbzrITQSe","title":"Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examples","pathname":"/paper_notes/oct/meta-dataset-a-dataset-of-datasets-for-learning-to-learn-from-few-examples","siteSpaceId":"sitesp_ySQ2C","description":"ICLR 20     10-23-2020","breadcrumbs":[{"label":"Oct"}]},{"id":"-MKXnZZy87VTPGKU1Yr6","title":"Conditional Neural Progress (CNPs)","pathname":"/paper_notes/oct/conditional-neural-progress","siteSpaceId":"sitesp_ySQ2C","description":"ICML 18   10-23-2020","breadcrumbs":[{"label":"Oct"}]},{"id":"-MK_QRbqWCoIcr5FvCL7","title":"Reviving and Improving Recurrent Back-Propagation","pathname":"/paper_notes/oct/reviving-and-improving-recurrent-back-propagation","siteSpaceId":"sitesp_ySQ2C","description":"ICML 18  10-26-2020","breadcrumbs":[{"label":"Oct"}]},{"id":"-MK_WYM65yFUrtAI5LLY","title":"Meta-Q-Learning","pathname":"/paper_notes/oct/meta-q-learning","siteSpaceId":"sitesp_ySQ2C","description":"ICLR 20 (Talk) 10-26-2020","breadcrumbs":[{"label":"Oct"}]},{"id":"-MLE17wqNybUlSUoNetR","title":"Learning Self-train for semi-supervised few shot classification","pathname":"/paper_notes/oct/learning-self-train-for-semi-supervised-few-shot-classification","siteSpaceId":"sitesp_ySQ2C","description":"NeurIPS 19  11/3/2020","breadcrumbs":[{"label":"Oct"}]},{"id":"-MLEAbDJz3-YMBzNAYmz","title":"Watch, Try, Learn: Meta-Learning from Demonstrations and Rewards","pathname":"/paper_notes/oct/watch-try-learn-meta-learning-from-demonstrations-and-rewards","siteSpaceId":"sitesp_ySQ2C","description":"ICLR 20, 11/3/2020","breadcrumbs":[{"label":"Oct"}]},{"id":"-MLhcyMJN3vH4EMB-sgI","title":"Neural Process","pathname":"/paper_notes/nov/neural-process","siteSpaceId":"sitesp_ySQ2C","description":"arxiv 18               11/9/2020","breadcrumbs":[{"label":"Nov"}]},{"id":"-MLhdFWL9H8eA-zKy8Fc","title":"Adversarially Robust Few-Shot Learning: A Meta-Learning Approach","pathname":"/paper_notes/nov/adversarially-robust-few-shot-learning-a-meta-learning-approach","siteSpaceId":"sitesp_ySQ2C","description":"NeurIPS 20  11/9/2020","breadcrumbs":[{"label":"Nov"}]},{"id":"-MMHTh7quGSixw1VAPJ-","title":"Learning to Adapt to Evolving Domains","pathname":"/paper_notes/nov/learning-to-adapt-to-evolving-domains","siteSpaceId":"sitesp_ySQ2C","description":"NeurIPS 2020    11-16-2020","breadcrumbs":[{"label":"Nov"}]},{"id":"-MFnbkvKVExiioLoqW6Y","title":"Relax constraints to continuous","pathname":"/paper_notes/tutorials/relax-constraints-to-continuous","siteSpaceId":"sitesp_ySQ2C","description":"","breadcrumbs":[{"label":"Tutorials"}]},{"id":"-MF9LZFE9GiSlzUts0k5","title":"MAML, FO-MAML, Reptile","pathname":"/paper_notes/tutorials/mathematical-details-in-maml-fo-maml-reptile","siteSpaceId":"sitesp_ySQ2C","description":"gradient optimization based meta-learning algorithms","breadcrumbs":[{"label":"Tutorials"}]},{"id":"-MF9MKLB25CsgLsozyEX","title":"Gradient Descent","pathname":"/paper_notes/tutorials/gradient-descent","siteSpaceId":"sitesp_ySQ2C","description":"","breadcrumbs":[{"label":"Tutorials"}]},{"id":"-MF9MQJ3ZDoFAlh9mpOH","title":"Steepest Gradient Descent","pathname":"/paper_notes/tutorials/gradient-descent/steepest-gradient-descent","siteSpaceId":"sitesp_ySQ2C","description":"","breadcrumbs":[{"label":"Tutorials"},{"label":"Gradient Descent"}]},{"id":"-MF9M64L8ZLp4Gg8Y4v3","title":"Conjugate Gradient Descent","pathname":"/paper_notes/tutorials/gradient-descent/conjugate-gradient-descent","siteSpaceId":"sitesp_ySQ2C","description":"","breadcrumbs":[{"label":"Tutorials"},{"label":"Gradient Descent"}]},{"id":"-MG5FbIWnXpPL46SD7jO","title":"KL, Entropy, MLE, ELBO","pathname":"/paper_notes/kl-entropy-mle","siteSpaceId":"sitesp_ySQ2C","description":""},{"id":"-MFXFiLn9Ke96Zwq3Rjt","title":"Python","pathname":"/paper_notes/coding-tricks/python","siteSpaceId":"sitesp_ySQ2C","description":"","breadcrumbs":[{"label":"Coding tricks"}]},{"id":"-MFXFTw9gvRVEXl1tGQ3","title":"Pytorch","pathname":"/paper_notes/coding-tricks/pytorch","siteSpaceId":"sitesp_ySQ2C","description":"","breadcrumbs":[{"label":"Coding tricks"}]},{"id":"-MZuXaqHJQDxL-YZlpIw","title":"kmeans","pathname":"/paper_notes/ml/kmeans","siteSpaceId":"sitesp_ySQ2C","description":"","breadcrumbs":[{"label":"ml"}]}]}