{"list":"other","total":84,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1412.6572","title":"Explaining and Harnessing Adversarial Examples","created":"2014-12-20","cited_by_count":7364},{"id":"1312.6199","title":"Intriguing properties of neural networks","created":"2013-12-21","cited_by_count":5155},{"id":"1611.01144","title":"Categorical Reparameterization with Gumbel-Softmax","created":"2016-11-03","cited_by_count":2739},{"id":"1907.02893","title":"Invariant Risk Minimization","created":"2019-07-05","cited_by_count":1854},{"id":"1912.02762","title":"Normalizing Flows for Probabilistic Modeling and Inference","created":"2019-12-05","cited_by_count":1323},{"id":"1811.12359","title":"Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations","created":"2018-11-29","cited_by_count":941},{"id":"1404.7828","title":"Deep Learning in Neural Networks: An Overview","created":"2014-04-30","cited_by_count":770},{"id":"1803.01422","title":"DAGs with NO TEARS: Continuous Optimization for Structure Learning","created":"2018-03-04","cited_by_count":752},{"id":"2003.00688","title":"Out-of-Distribution Generalization via Risk Extrapolation (REx)","created":"2020-03-02","cited_by_count":742},{"id":"1807.04975","title":"Recognition in Terra Incognita","created":"2018-07-13","cited_by_count":658},{"id":"1301.2115","title":"Domain Generalization via Invariant Feature Representation","created":"2013-01-10","cited_by_count":623},{"id":"1906.04032","title":"Neural Spline Flows","created":"2019-06-10","cited_by_count":596},{"id":"1501.01332","title":"Causal inference using invariant prediction: identification and confidence intervals","created":"2015-01-06","cited_by_count":536},{"id":"1907.04809","title":"Variational Autoencoders and Nonlinear ICA: A Unifying Framework","created":"2019-07-10","cited_by_count":503},{"id":"2106.04619","title":"Self-Supervised Learning with Data Augmentations Provably Isolates Content from Style","created":"2021-06-08","cited_by_count":312},{"id":"1805.08651","title":"Nonlinear ICA Using Auxiliary Variables and Generalized Contrastive Learning","created":"2018-05-22","cited_by_count":282},{"id":"1605.06336","title":"Unsupervised Feature Extraction by Time-Contrastive Learning and Nonlinear ICA","created":"2016-05-20","cited_by_count":273},{"id":"1911.10500","title":"Causality for Machine Learning","created":"2019-11-24","cited_by_count":243},{"id":"2002.02886","title":"Weakly-Supervised Disentanglement Without Compromises","created":"2020-02-07","cited_by_count":239},{"id":"2102.08850","title":"Contrastive Learning Inverts the Data Generating Process","created":"2021-02-17","cited_by_count":221},{"id":"2007.01754","title":"Differentiable Causal Discovery from Interventional Data","created":"2020-07-03","cited_by_count":218},{"id":"1909.13189","title":"Learning Sparse Nonparametric DAGs","created":"2019-09-29","cited_by_count":207},{"id":"1903.01672","title":"Causal Discovery from Heterogeneous/Nonstationary Data with Independent Changes","created":"2019-03-05","cited_by_count":166},{"id":"2107.10098","title":"Disentanglement via Mechanism Sparsity Regularization: A New Principle for Nonlinear ICA","created":"2021-07-21","cited_by_count":160},{"id":"2209.11924","title":"Interventional Causal Representation Learning","created":"2022-09-24","cited_by_count":142},{"id":"1706.08576","title":"Invariant Causal Prediction for Nonlinear Models","created":"2017-06-26","cited_by_count":140},{"id":"2203.16437","title":"Weakly supervised causal representation learning","created":"2022-03-30","cited_by_count":140},{"id":"2102.10395","title":"On Calibration and Out-of-domain Generalization","created":"2021-02-20","cited_by_count":134},{"id":"2202.03169","title":"CITRIS: Causal Identifiability from Temporal Intervened Sequences","created":"2022-02-07","cited_by_count":133},{"id":"2007.10930","title":"Towards Nonlinear Disentanglement in Natural Data with Temporal Sparse Coding","created":"2020-07-21","cited_by_count":122},{"id":"1707.00819","title":"Causal Consistency of Structural Equation Models","created":"2017-07-04","cited_by_count":118},{"id":"1801.06229","title":"Anchor regression: heterogeneous data meets causality","created":"2018-01-18","cited_by_count":118},{"id":"1812.03789","title":"Abstracting Causal Models","created":"2018-12-10","cited_by_count":107},{"id":"2007.00810","title":"On Linear Identifiability of Learned Representations","created":"2020-07-01","cited_by_count":105},{"id":"2002.11537","title":"ICE-BeeM: Identifiable Conditional Energy-Based Deep Models Based on Nonlinear ICA","created":"2020-02-26","cited_by_count":102},{"id":"2110.05428","title":"Learning Temporally Causal Latent Processes from General Temporal Data","created":"2021-10-11","cited_by_count":98},{"id":"2106.05200","title":"Independent mechanism analysis, a new concept?","created":"2021-06-09","cited_by_count":97},{"id":"2001.04872","title":"Disentanglement by Nonlinear ICA with General Incompressible-flow Networks (GIN)","created":"2020-01-14","cited_by_count":92},{"id":"1905.06642","title":"The Incomplete Rosetta Stone Problem: Identifiability Results for Multi-View Nonlinear ICA","created":"2019-05-16","cited_by_count":86},{"id":"2211.16467","title":"Linear Causal Disentanglement via Interventions","created":"2022-11-29","cited_by_count":84},{"id":"1910.09772","title":"Weakly Supervised Disentanglement with Guarantees","created":"2019-10-22","cited_by_count":82},{"id":"1605.08179","title":"Discovering Causal Signals in Images","created":"2016-05-26","cited_by_count":79},{"id":"2006.12107","title":"Hidden Markov Nonlinear ICA: Unsupervised Learning from Nonstationary Time Series","created":"2020-06-22","cited_by_count":77},{"id":"2109.03795","title":"Desiderata for Representation Learning: A Causal Perspective","created":"2021-09-08","cited_by_count":76},{"id":"1503.01603","title":"External Validity: From Do-Calculus to Transportability Across Populations","created":"2015-03-05","cited_by_count":75},{"id":"2206.10044","title":"Identifiability of deep generative models without auxiliary information","created":"2022-06-20","cited_by_count":70},{"id":"2010.02637","title":"Weakly Supervised Disentangled Generative Causal Representation Learning","created":"2020-10-06","cited_by_count":68},{"id":"2207.09944","title":"Probable Domain Generalization via Quantile Risk Minimization","created":"2022-07-20","cited_by_count":66},{"id":"2206.01101","title":"Weakly Supervised Representation Learning with Sparse Perturbations","created":"2022-06-02","cited_by_count":65},{"id":"2106.09620","title":"Disentangling Identifiable Features from Noisy Data with Structured Nonlinear ICA","created":"2021-06-17","cited_by_count":64},{"id":"1906.11583","title":"Approximate Causal Abstraction","created":"2019-06-27","cited_by_count":63},{"id":"2210.13647","title":"Temporally Disentangled Representation Learning","created":"2022-10-24","cited_by_count":61},{"id":"1412.2309","title":"Visual Causal Feature Learning","created":"2014-12-07","cited_by_count":59},{"id":"2210.09054","title":"On the Identifiability and Estimation of Causal Location-Scale Noise Models","created":"2022-10-13","cited_by_count":56},{"id":"2305.17225","title":"Causal Component Analysis","created":"2023-05-26","cited_by_count":56},{"id":"2106.15563","title":"Learning latent causal graphs via mixture oracles","created":"2021-06-29","cited_by_count":55},{"id":"2206.02013","title":"Causal Discovery in Heterogeneous Environments Under the Sparse Mechanism Shift Hypothesis","created":"2022-06-04","cited_by_count":55},{"id":"2110.10804","title":"Identifiable Deep Generative Models via Sparse Decoding","created":"2021-10-20","cited_by_count":54},{"id":"2208.06406","title":"Function Classes for Identifiable Nonlinear Independent Component Analysis","created":"2022-08-12","cited_by_count":53},{"id":"1301.2312","title":"Causal Discovery from Changes","created":"2013-01-10","cited_by_count":52},{"id":"2206.06169","title":"Causal Representation Learning for Instantaneous and Temporal Effects in Interactive Systems","created":"2022-06-13","cited_by_count":51},{"id":"2301.08230","title":"Score-based Causal Representation Learning with Interventions","created":"2023-01-19","cited_by_count":49},{"id":"2303.16535","title":"Nonlinear Independent Component Analysis for Principled Disentanglement in Unsupervised Deep Learning","created":"2023-03-29","cited_by_count":48},{"id":"2206.01152","title":"Causal Structure Learning: a Combinatorial Perspective","created":"2022-06-02","cited_by_count":46},{"id":"2305.14229","title":"Provably Learning Object-Centric Representations","created":"2023-05-23","cited_by_count":45},{"id":"2211.14666","title":"Synergies between Disentanglement and Sparsity: Generalization and Identifiability in Multi-Task Learning","created":"2022-11-26","cited_by_count":44},{"id":"2102.08208","title":"Conditional Distributional Treatment Effect with Kernel Conditional Mean Embeddings and U-Statistic Regression","created":"2021-02-16","cited_by_count":40},{"id":"2204.00607","title":"From Statistical to Causal Learning","created":"2022-04-01","cited_by_count":40},{"id":"2205.13085","title":"Identifying Patient-Specific Root Causes with the Heteroscedastic Noise Model","created":"2022-05-25","cited_by_count":38},{"id":"2210.07347","title":"Disentanglement of Correlated Factors via Hausdorff Factorized Support","created":"2022-10-13","cited_by_count":37},{"id":"2208.14153","title":"Identifying Weight-Variant Latent Causal Models","created":"2022-08-30","cited_by_count":34},{"id":"2206.00801","title":"Indeterminacy in Generative Models: Characterization and Strong Identifiability","created":"2022-06-02","cited_by_count":33},{"id":"1512.07942","title":"Multi-Level Cause-Effect Systems","created":"2015-12-25","cited_by_count":30},{"id":"2110.15796","title":"Properties from Mechanisms: An Equivariance Perspective on Identifiable Representation Learning","created":"2021-10-29","cited_by_count":30},{"id":"2207.07732","title":"Partial Disentanglement via Mechanism Sparsity","created":"2022-07-15","cited_by_count":29},{"id":"2204.12363","title":"Causal Transportability for Visual Recognition","created":"2022-04-26","cited_by_count":23},{"id":"2210.00364","title":"DCI-ES: An Extended Disentanglement Framework with Connections to Identifiability","created":"2022-10-01","cited_by_count":23},{"id":"2301.05893","title":"Jointly Learning Consistent Causal Abstractions Over Multiple Interventional Distributions","created":"2023-01-14","cited_by_count":23},{"id":"1705.02212","title":"Group invariance principles for causal generative models","created":"2017-05-05","cited_by_count":20},{"id":"2006.15090","title":"Relative gradient optimization of the Jacobian term in unsupervised deep learning","created":"2020-06-26","cited_by_count":16},{"id":"2207.08603","title":"Abstraction between Structural Causal Models: A Review of Definitions and Properties","created":"2022-07-18","cited_by_count":15},{"id":"2204.04606","title":"Towards efficient representation identification in supervised learning","created":"2022-04-10","cited_by_count":14}],"next_cursor":null}