| 2025 | ICML | Density Ratio Estimation with Conditional Probability Paths. | Hanlin Yu, Arto Klami, Aapo Hyvrinen, Anna Korba, Omar Chehab |
| 2024 | AISTATS | Identifiable Feature Learning for Spatial Data with Nonlinear ICA. | Hermanni Hlv, Jonathan So, Richard E. Turner, Aapo Hyvrinen |
| 2024 | ICML | Causal Representation Learning Made Identifiable by Grouping of Observational Variables. | Hiroshi Morioka, Aapo Hyvrinen |
| 2023 | AISTATS | Connectivity-contrastive learning: Combining causal discovery and representation learning for multimodal data. | Hiroshi Morioka, Aapo Hyvrinen |
| 2022 | UAI | The optimal noise in noise-contrastive learning is not what you think. | Omar Chehab, Alexandre Gramfort, Aapo Hyvrinen |
| 2022 | UAI | Binary independent component analysis: a non-stationarity-based approach. | Antti Hyttinen, Vitria Barin Pacela, Aapo Hyvrinen |
| 2021 | AISTATS | Causal Autoregressive Flows. | Ilyes Khemakhem, Ricardo Pio Monti, Robert Leech, Aapo Hyvrinen |
| 2021 | AISTATS | Independent Innovation Analysis for Nonlinear Vector Autoregressive Process. | Hiroshi Morioka, Hermanni Hlv, Aapo Hyvrinen |
| 2020 | AISTATS | Variational Autoencoders and Nonlinear ICA: A Unifying Framework. | Ilyes Khemakhem, Diederik P. Kingma, Ricardo Pio Monti, Aapo Hyvrinen |
| 2020 | KDD | Preface: The 2020 ACM SIGKDD Workshop on Causal Discovery. | Thuc Duy Le, Lin Liu, Kun Zhang, Emre Kiciman, Peng Cui, Aapo Hyvrinen |
| 2020 | UAI | Hidden Markov Nonlinear ICA: Unsupervised Learning from Nonstationary Time Series. | Hermanni Hlv, Aapo Hyvrinen |
| 2020 | UAI | Robust contrastive learning and nonlinear ICA in the presence of outliers. | Hiroaki Sasaki, Takashi Takenouchi, Ricardo Pio Monti, Aapo Hyvrinen |
| 2019 | AISTATS | Nonlinear ICA Using Auxiliary Variables and Generalized Contrastive Learning. | Aapo Hyvrinen, Hiroaki Sasaki, Richard E. Turner |
| 2019 | AISTATS | Estimation of Non-Normalized Mixture Models. | Takeru Matsuda, Aapo Hyvrinen |
| 2019 | KDD | Preface: The 2019 ACM SIGKDD Workshop on Causal Discovery. | Thuc Duy Le, Jiuyong Li, Kun Zhang, Emre Kiciman, Peng Cui, Aapo Hyvrinen |
| 2019 | UAI | Causal Discovery with General Non-Linear Relationships using Non-Linear ICA. | Ricardo Pio Monti, Kun Zhang, Aapo Hyvrinen |
| 2018 | KDD | Preface: The 2018 ACM SIGKDD Workshop on Causal Discovery. | Thuc Duy Le, Kun Zhang, Emre Kiciman, Aapo Hyvrinen, Lin Liu |
| 2018 | UAI | A unified probabilistic model for learning latent factors and their connectivities from high-dimensional data . | Ricardo Pio Monti, Aapo Hyvrinen |
| 2017 | AISTATS | Nonlinear ICA of Temporally Dependent Stationary Sources. | Aapo Hyvrinen, Hiroshi Morioka |
| 2017 | ICML | SPLICE: Fully Tractable Hierarchical Extension of ICA with Pooling. | Junichiro Hirayama, Aapo Hyvrinen, Motoaki Kawanabe |
| 2015 | IJCNN | Independent component analysis with an inverse problem motivated penalty term. | Jouni Puuronen, Aapo Hyvrinen |
| 2014 | AISTATS | Estimating Dependency Structures for non-Gaussian Components with Linear and Energy Correlations. | Hiroaki Sasaki, Michael Gutmann, Hayaru Shouno, Aapo Hyvrinen |
| 2012 | ICANN | Estimation of Causal Orders in a Linear Non-Gaussian Acyclic Model: A Method Robust against Latent Confounders. | Tatsuya Tashiro, Shohei Shimizu, Aapo Hyvrinen, Takashi Washio |
| 2012 | ICPR | Learning a selectivity-invariance-selectivity feature extraction architecture for images. | Michael Gutmann, Aapo Hyvrinen |
| 2011 | ICANN | Extracting Coactivated Features from Multiple Data Sets. | Michael Gutmann, Aapo Hyvrinen |
| 2011 | ICANN | Complex-Valued Independent Component Analysis of Natural Images. | Valero Laparra, Michael Gutmann, Jess Malo, Aapo Hyvrinen |
| 2011 | ICANN | Hermite Polynomials and Measures of Non-gaussianity. | Jouni Puuronen, Aapo Hyvrinen |
| 2010 | ICANN | Discovery of Exogenous Variables in Data with More Variables Than Observations. | Yasuhiro Sogawa, Shohei Shimizu, Aapo Hyvrinen, Takashi Washio, Teppei Shimamura, Seiya Imoto |
| 2010 | ICONIP | Sparse and Low-Rank Estimation of Time-Varying Markov Networks with Alternating Direction Method of Multipliers. | Junichiro Hirayama, Aapo Hyvrinen, Shin Ishii |
| 2010 | UAI | A Family of Computationally E cient and Simple Estimators for Unnormalized Statistical Models. | Miika Pihlaja, Michael Gutmann, Aapo Hyvrinen |
| 2010 | UAI | Source Separation and Higher-Order Causal Analysis of MEG and EEG. | Kun Zhang, Aapo Hyvrinen |
| 2009 | ESANN | Learning reconstruction and prediction of natural stimuli by a population of spiking neurons. | Michael Gutmann, Aapo Hyvrinen |
| 2009 | ICANN | Learning Features by Contrasting Natural Images with Noise. | Michael Gutmann, Aapo Hyvrinen |
| 2009 | ICANN | Modelling Image Complexity by Independent Component Analysis, with Application to Content-Based Image Retrieval. | Jukka Perki, Aapo Hyvrinen |
| 2009 | IDA | Learning Natural Image Structure with a Horizontal Product Model. | Urs Kster, Jussi T. Lindgren, Michael Gutmann, Aapo Hyvrinen |
| 2009 | IDA | Estimating Markov Random Field Potentials for Natural Images. | Urs Kster, Jussi T. Lindgren, Aapo Hyvrinen |
| 2009 | IDA | ICA with Sparse Connections: Revisited. | Kun Zhang, Heng Peng, Laiwan Chan, Aapo Hyvrinen |
| 2009 | UAI | A direct method for estimating a causal ordering in a linear non-Gaussian acyclic model. | Shohei Shimizu, Aapo Hyvrinen, Yoshinobu Kawahara |
| 2009 | UAI | On the Identifiability of the Post-Nonlinear Causal Model. | Kun Zhang, Aapo Hyvrinen |
| 2008 | ICML | Causal modelling combining instantaneous and lagged effects: an identifiable model based on non-Gaussianity. | Aapo Hyvrinen, Shohei Shimizu, Patrik O. Hoyer |
| 2008 | IJCNN | Learning encoding and decoding filters for data representation with a spiking neuron. | Michael Gutmann, Aapo Hyvrinen, Kazuyuki Aihara |
| 2008 | IJCNN | On the learning of nonlinear visual features from natural images by optimizing response energies. | Jussi T. Lindgren, Aapo Hyvrinen |
| 2008 | IJCNN | Unsupervised learning of dependencies between local luminance and contrast in natural images. | Jussi T. Lindgren, Jarmo Hurri, Aapo Hyvrinen |
| 2008 | UAI | Causal discovery of linear acyclic models with arbitrary distributions. | Patrik O. Hoyer, Aapo Hyvrinen, Richard Scheines, Peter Spirtes, Joseph D. Ramsey, Gustavo Lacerda, Shohei Shimizu |
| 2007 | ICANN | A Two-Layer ICA-Like Model Estimated by Score Matching. | Urs Kster, Aapo Hyvrinen |
| 2007 | ICONIP | Discovery of Linear Non-Gaussian Acyclic Models in the Presence of Latent Classes. | Shohei Shimizu, Aapo Hyvrinen |
| 2006 | ESANN | FastISA: A fast fixed-point algorithm for independent subspace analysis. | Aapo Hyvrinen, Urs Kster |
| 2006 | ICANN | A Quasi-stochastic Gradient Algorithm for Variance-Dependent Component Analysis. | Aapo Hyvrinen, Shohei Shimizu |
| 2006 | IJCNN | Learning to Segment Any Random Vector. | Aapo Hyvrinen, Jukka Perki |
| 2005 | UAI | Discovery of Non-gaussian Linear Causal Models using ICA. | Shohei Shimizu, Aapo Hyvrinen, Yutaka Kano, Patrik O. Hoyer |
| 2004 | ICPR | Learning High-level Independent Components of Images through a Spectral Representation. | Jussi T. Lindgren, Aapo Hyvrinen |
| 2004 | IJCNN | Linguistic feature extraction using independent component analysis. | Timo Honkela, Aapo Hyvrinen |
| 2002 | ICANN | Receptive Fields Similar to Simple Cells Maximize Temporal Coherence in Natural Video. | Jarmo Hurri, Aapo Hyvrinen |
| 2000 | IJCNN | ICA of Complex Valued Signals: A Fast and Robust Deflationary Algorithm. | Ella Bingham, Aapo Hyvrinen |
| 2000 | IJCNN | Feature Extraction from Color and Stereo Images Using ICA. | Patrik O. Hoyer, Aapo Hyvrinen |
| 2000 | IJCNN | Topographic ICA as a Model of V1 Receptive Fields. | Aapo Hyvrinen, Patrik O. Hoyer, Mika Inki |
| 1999 | IJCNN | Estimating signal-adapted wavelets using sparseness criteria. | Patrik O. Hoyer, Aapo Hyvrinen |
| 1999 | IJCNN | A fast algorithm for estimating overcomplete ICA bases for image windows. | Aapo Hyvrinen, Razvan Cristescu, Erkki Oja |
| 1999 | IJCNN | Independent subspace analysis shows emergence of phase and shift invariant features from natural images. | Aapo Hyvrinen, Patrik O. Hoyer |
| 1999 | ISCAS | Fast ICA for noisy data using Gaussian moments. | Aapo Hyvrinen |
| 1998 | ICPR | Image feature extraction by sparse coding and independent component analysis. | Aapo Hyvrinen, Erkki Oja, Patrik O. Hoyer, Jarmo Hurri |
| 1997 | ICANN | From Neural Principal Components to Neural Independent Components. | Erkki Oja, Juha Karhunen, Aapo Hyvrinen |
| 1997 | ICASSP | A family of fixed-point algorithms for independent component analysis. | Aapo Hyvrinen |
| 1997 | ICASSP | Applications of neural blind separation to signal and image processing. | Juha Karhunen, Aapo Hyvrinen, Ricardo Vigrio, Jarmo Hurri, Erkki Oja |
| 1996 | ICANN | Purely Logical Neural Principal Component and Independent Component Learning. | Aapo Hyvrinen |