Michalis K. Titsias

95 papers A* 17A 11B 1C 2Journal 45Unranked 17

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Correction to: Personalized federated learning with exact stochastic gradient descent. Appl. Intell. Sotirios Nikoloutsopoulos, Iordanis Koutsopoulos, Michalis K. Titsias
2025	J	`jnl`	Demystifying Diffusion Objectives: Reweighted Losses are Better Variational Bounds. CoRR Jiaxin Shi, Michalis K. Titsias
2025	J	`jnl`	Gaussian Invariant Markov Chain Monte Carlo. CoRR Michalis K. Titsias, Angelos Alexopoulos, Siran Liu, Petros Dellaportas
2025	A*	`conf`	Learning-Order Autoregressive Models with Application to Molecular Graph Generation. ICML Zhe Wang, Jiaxin Shi, Nicolas Heess, Arthur Gretton, Michalis K. Titsias
2025	J	`jnl`	Learning-Order Autoregressive Models with Application to Molecular Graph Generation. CoRR Zhe Wang, Jiaxin Shi, Nicolas Heess, Arthur Gretton, Michalis K. Titsias
2025	A*	`conf`	New Bounds for Sparse Variational Gaussian Processes. ICML Michalis K. Titsias
2025	J	`jnl`	New Bounds for Sparse Variational Gaussian Processes. CoRR Michalis K. Titsias
2025	J	`jnl`	Personalized federated learning with exact stochastic gradient descent. Appl. Intell. Sotirios Nikoloutsopoulos, Iordanis Koutsopoulos, Michalis K. Titsias
2025	J	`jnl`	Sparse Gaussian Processes: Structured Approximations and Power-EP Revisited. CoRR Thang D. Bui, Michalis K. Titsias
2024	J	`jnl`	Can independent Metropolis beat crude Monte Carlo? CoRR Siran Liu, Petros Dellaportas, Michalis K. Titsias
2024	A*	`conf`	Kalman Filter for Online Classification of Non-Stationary Data. ICLR Michalis K. Titsias, Alexandre Galashov, Amal Rannen-Triki, Razvan Pascanu, Yee Whye Teh, Jörg Bornschein
2024	A*	`conf`	Non-Stationary Learning of Neural Networks with Automatic Soft Parameter Reset. NeurIPS Alexandre Galashov, Michalis K. Titsias, András György, Clare Lyle, Razvan Pascanu, Yee Whye Teh, Maneesh Sahani
2024	J	`jnl`	Non-Stationary Learning of Neural Networks with Automatic Soft Parameter Reset. CoRR Alexandre Galashov, Michalis K. Titsias, András György, Clare Lyle, Razvan Pascanu, Yee Whye Teh, Maneesh Sahani
2024	J	`jnl`	Revisiting Dynamic Evaluation: Online Adaptation for Large Language Models. CoRR Amal Rannen-Triki, Jörg Bornschein, Razvan Pascanu, Marcus Hutter, András György, Alexandre Galashov, Yee Whye Teh, Michalis K. Titsias
2024	A*	`conf`	Simplified and Generalized Masked Diffusion for Discrete Data. NeurIPS Jiaxin Shi, Kehang Han, Zhe Wang, Arnaud Doucet, Michalis K. Titsias
2024	J	`jnl`	Simplified and Generalized Masked Diffusion for Discrete Data. CoRR Jiaxin Shi, Kehang Han, Zhe Wang, Arnaud Doucet, Michalis K. Titsias
2023	J	`jnl`	Kalman Filter for Online Classification of Non-Stationary Data. CoRR Michalis K. Titsias, Alexandre Galashov, Amal Rannen-Triki, Razvan Pascanu, Yee Whye Teh, Jörg Bornschein
2023	A*	`conf`	Optimal Preconditioning and Fisher Adaptive Langevin Sampling. NeurIPS Michalis K. Titsias
2023	J	`jnl`	Optimal Preconditioning and Fisher Adaptive Langevin Sampling. CoRR Michalis K. Titsias
2023	J	`jnl`	Variance reduction for Metropolis-Hastings samplers. Stat. Comput. Angelos Alexopoulos, Petros Dellaportas, Michalis K. Titsias
2022	A	`conf`	Double Control Variates for Gradient Estimation in Discrete Latent Variable Models. AISTATS Michalis K. Titsias, Jiaxin Shi
2022	A*	`conf`	Gradient Estimation with Discrete Stein Operators. NeurIPS Jiaxin Shi, Yuhao Zhou, Jessica Hwang, Michalis K. Titsias, Lester Mackey
2022	J	`jnl`	Gradient Estimation with Discrete Stein Operators. CoRR Jiaxin Shi, Yuhao Zhou, Jessica Hwang, Michalis K. Titsias, Lester Mackey
2022	A*	`conf`	Information-theoretic Online Memory Selection for Continual Learning. ICLR Shengyang Sun, Daniele Calandriello, Huiyi Hu, Ang Li, Michalis K. Titsias
2022	J	`jnl`	Information-theoretic Online Memory Selection for Continual Learning. CoRR Shengyang Sun, Daniele Calandriello, Huiyi Hu, Ang Li, Michalis K. Titsias
2022	J	`jnl`	Personalized Federated Learning with Exact Stochastic Gradient Descent. CoRR Sotirios Nikoloutsopoulos, Iordanis Koutsopoulos, Michalis K. Titsias
2022	J	`jnl`	Sequential changepoint detection in neural networks with checkpoints. Stat. Comput. Michalis K. Titsias, Jakub Sygnowski, Yutian Chen
2021	J	`jnl`	Double Control Variates for Gradient Estimation in Discrete Latent Variable Models. CoRR Michalis K. Titsias, Jiaxin Shi
2021	A*	`conf`	Entropy-based adaptive Hamiltonian Monte Carlo. NeurIPS Marcel Hirt, Michalis K. Titsias, Petros Dellaportas
2021	A	`conf`	Information theoretic meta learning with Gaussian processes. UAI Michalis K. Titsias, Francisco J. R. Ruiz, Sotirios Nikoloutsopoulos, Alexandre Galashov
2021	J	`jnl`	Large scale multi-label learning using Gaussian processes. Mach. Learn. Aristeidis Panos, Petros Dellaportas, Michalis K. Titsias
2021	A	`conf`	Unbiased gradient estimation for variational auto-encoders using coupled Markov chains. UAI Francisco J. R. Ruiz, Michalis K. Titsias, A. Taylan Cemgil, Arnaud Doucet
2020	A*	`conf`	Functional Regularisation for Continual Learning with Gaussian Processes. ICLR Michalis K. Titsias, Jonathan Schwarz, Alexander G. de G. Matthews, Razvan Pascanu, Yee Whye Teh
2020	J	`jnl`	Information Theoretic Meta Learning with Gaussian Processes. CoRR Michalis K. Titsias, Sotirios Nikoloutsopoulos, Alexandre Galashov
2020	J	`jnl`	Sequential Changepoint Detection in Neural Networks with Checkpoints. CoRR Michalis K. Titsias, Jakub Sygnowski, Yutian Chen
2020	A	`conf`	Sparse Orthogonal Variational Inference for Gaussian Processes. AISTATS Jiaxin Shi, Michalis K. Titsias, Andriy Mnih
2020	J	`jnl`	Unbiased Gradient Estimation for Variational Auto-Encoders using Coupled Markov Chains. CoRR Francisco J. R. Ruiz, Michalis K. Titsias, A. Taylan Cemgil, Arnaud Doucet
2019	A*	`conf`	A Contrastive Divergence for Combining Variational Inference and MCMC. ICML Francisco J. R. Ruiz, Michalis K. Titsias
2019	J	`jnl`	A Contrastive Divergence for Combining Variational Inference and MCMC. CoRR Francisco J. R. Ruiz, Michalis K. Titsias
2019	A	`conf`	Augmented Ensemble MCMC sampling in Factorial Hidden Markov Models. AISTATS Kaspar Märtens, Michalis K. Titsias, Christopher Yau
2019	J	`jnl`	Functional Regularisation for Continual Learning using Gaussian Processes. CoRR Michalis K. Titsias, Jonathan Schwarz, Alexander G. de G. Matthews, Razvan Pascanu, Yee Whye Teh
2019	A*	`conf`	Gradient-based Adaptive Markov Chain Monte Carlo. NeurIPS Michalis K. Titsias, Petros Dellaportas
2019	J	`jnl`	Gradient-based Adaptive Markov Chain Monte Carlo. CoRR Michalis K. Titsias, Petros Dellaportas
2019	J	`jnl`	Prescribed Generative Adversarial Networks. CoRR Adji B. Dieng, Francisco J. R. Ruiz, David M. Blei, Michalis K. Titsias
2019	J	`jnl`	Sparse Orthogonal Variational Inference for Gaussian Processes. CoRR Jiaxin Shi, Michalis K. Titsias, Andriy Mnih
2019	A	`conf`	Unbiased Implicit Variational Inference. AISTATS Michalis K. Titsias, Francisco J. R. Ruiz
2018	A*	`conf`	Augment and Reduce: Stochastic Inference for Large Categorical Distributions. ICML Francisco J. R. Ruiz, Michalis K. Titsias, Adji B. Dieng, David M. Blei
2018	J	`jnl`	Augment and Reduce: Stochastic Inference for Large Categorical Distributions. CoRR Francisco J. R. Ruiz, Michalis K. Titsias, Adji B. Dieng, David M. Blei
2018	J	`jnl`	Bayesian Transfer Reinforcement Learning with Prior Knowledge Rules. CoRR Michalis K. Titsias, Sotirios Nikoloutsopoulos
2018	J	`jnl`	Fully Scalable Gaussian Processes using Subspace Inducing Inputs. CoRR Aristeidis Panos, Petros Dellaportas, Michalis K. Titsias
2018	J	`jnl`	Unbiased Implicit Variational Inference. CoRR Michalis K. Titsias, Francisco J. R. Ruiz
2017	A*	`conf`	Bayesian Boolean Matrix Factorisation. ICML Tammo Rukat, Christopher C. Holmes, Michalis K. Titsias, Christopher Yau
2017	J	`jnl`	Bayesian Boolean Matrix Factorisation. CoRR Tammo Rukat, Christopher C. Holmes, Michalis K. Titsias, Christopher Yau
2016	B	`conf`	First learn then earn: optimizing mobile crowdsensing campaigns through data-driven user profiling. MobiHoc Merkourios Karaliopoulos, Iordanis Koutsopoulos, Michalis K. Titsias
2016	—	`conf`	One-vs-Each Approximation to Softmax for Scalable Estimation of Probabilities. NIPS Michalis K. Titsias
2016	A	`conf`	Overdispersed Black-Box Variational Inference. UAI Francisco J. R. Ruiz, Michalis K. Titsias, David M. Blei
2016	—	`conf`	Short-Term Load Forecasting using a Cluster of Neural Networks for the Greek Energy Market. SETN Apostolos N. Adamakos, Michalis K. Titsias
2016	—	`conf`	The Generalized Reparameterization Gradient. NIPS Francisco J. R. Ruiz, Michalis K. Titsias, David M. Blei
2016	J	`jnl`	Variational Inference for Latent Variables and Uncertain Inputs in Gaussian Processes. J. Mach. Learn. Res. Andreas C. Damianou, Michalis K. Titsias, Neil D. Lawrence
2015	—	`conf`	Inference for determinantal point processes without spectral knowledge. NIPS Rémi Bardenet, Michalis K. Titsias
2015	—	`conf`	Local Expectation Gradients for Black Box Variational Inference. NIPS Michalis K. Titsias, Miguel Lázaro-Gredilla
2014	A*	`conf`	Doubly Stochastic Variational Bayes for non-Conjugate Inference. ICML Michalis K. Titsias, Miguel Lázaro-Gredilla
2014	—	`conf`	Hamming Ball Auxiliary Sampling for Factorial Hidden Markov Models. NIPS Michalis K. Titsias, Christopher Yau
2014	J	`jnl`	Retrieval of Biophysical Parameters With Heteroscedastic Gaussian Processes. IEEE Geosci. Remote. Sens. Lett. Miguel Lázaro-Gredilla, Michalis K. Titsias, Jochem Verrelst, Gustavo Camps-Valls
2014	J	`jnl`	Variational Inference for Uncertainty on the Inputs of Gaussian Process Models. CoRR Andreas C. Damianou, Michalis K. Titsias, Neil D. Lawrence
2013	C	`conf`	Estimation of vegetation chlorophyll content with Variational Heteroscedastic Gaussian Processes. IGARSS Miguel Lázaro-Gredilla, Michalis K. Titsias, Jochem Verrelst, Gustavo Camps-Valls
2013	J	`jnl`	Statistical Inference in Hidden Markov Models using $k$-segment Constraints. CoRR Michalis K. Titsias, Christopher Yau, Christopher C. Holmes
2013	—	`conf`	Variational Inference for Mahalanobis Distance Metrics in Gaussian Process Regression. NIPS Michalis K. Titsias, Miguel Lázaro-Gredilla
2012	J	`jnl`	Identifying targets of multiple co-regulating transcription factors from expression time-series by Bayesian model comparison. BMC Syst. Biol. Michalis K. Titsias, Antti Honkela, Neil D. Lawrence, Magnus Rattray
2012	J	`jnl`	Manifold Relevance Determination CoRR Andreas C. Damianou, Carl Henrik Ek, Michalis K. Titsias, Neil D. Lawrence
2012	A*	`conf`	Manifold Relevance Determination. ICML Andreas C. Damianou, Carl Henrik Ek, Michalis K. Titsias, Neil D. Lawrence
2011	—	`conf`	Spike and Slab Variational Inference for Multi-Task and Multiple Kernel Learning. NIPS Michalis K. Titsias, Miguel Lázaro-Gredilla
2011	J	`jnl`	Variational Gaussian Process Dynamical Systems CoRR Andreas C. Damianou, Michalis K. Titsias, Neil D. Lawrence
2011	—	`conf`	Variational Gaussian Process Dynamical Systems. NIPS Andreas C. Damianou, Michalis K. Titsias, Neil D. Lawrence
2011	A*	`conf`	Variational Heteroscedastic Gaussian Process Regression. ICML Miguel Lázaro-Gredilla, Michalis K. Titsias
2010	A	`conf`	Bayesian Gaussian Process Latent Variable Model. AISTATS Michalis K. Titsias, Neil D. Lawrence
2010	A	`conf`	Efficient Multioutput Gaussian Processes through Variational Inducing Kernels. AISTATS Mauricio A. Álvarez, David Luengo, Michalis K. Titsias, Neil D. Lawrence
2010	—	`ch.`	Gaussian Processes for Missing Species in Biochemical Systems. Learning and Inference in Computational Systems Biology Neil D. Lawrence, Magnus Rattray, Pei Gao, Michalis K. Titsias
2009	A	`conf`	Variational Learning of Inducing Variables in Sparse Gaussian Processes. AISTATS Michalis K. Titsias
2009	C	`conf`	Web Page Rank Prediction with PCA and EM Clustering. WAW Polyxeni Zacharouli, Michalis K. Titsias, Michalis Vazirgiannis
2008	—	`conf`	Efficient Sampling for Gaussian Process Inference using Control Variables. NIPS Michalis K. Titsias, Neil D. Lawrence, Magnus Rattray
2007	—	`conf`	The Infinite Gamma-Poisson Feature Model. NIPS Michalis K. Titsias
2006	J	`jnl`	Bayesian Feature and Model Selection for Gaussian Mixture Models. IEEE Trans. Pattern Anal. Mach. Intell. Constantinos Constantinopoulos, Michalis K. Titsias, Aristidis Likas
2006	—	`conf`	Sequential Learning of Layered Models from Video. Toward Category-Level Object Recognition Michalis K. Titsias, Christopher K. I. Williams
2005	A	`conf`	Fast Learning of Sprites using Invariant Features. BMVC Moray Allan, Michalis K. Titsias, Christopher K. I. Williams
2005	—	`conf`	Unsupervised Learning of Multiple Aspects of Moving Objects from Video. Panhellenic Conference on Informatics Michalis K. Titsias, Christopher K. I. Williams
2005	—	`—`	Unsupervised learning of multiple objects in images. Michalis K. Titsias
2004	—	`conf`	Fast Unsupervised Greedy Learning of Multiple Objects and Parts from Video. CVPR Workshops Michalis K. Titsias, Christopher K. I. Williams
2004	J	`jnl`	Greedy Learning of Multiple Objects in Images Using Robust Statistics and Factorial Learning. Neural Comput. Christopher K. I. Williams, Michalis K. Titsias
2003	J	`jnl`	Class Conditional Density Estimation Using Mixtures with Constrained Component Sharing. IEEE Trans. Pattern Anal. Mach. Intell. Michalis K. Titsias, Aristidis Likas
2002	—	`conf`	A Bayesian Regularization Method for the Probabilistic RBF Network. SETN Constantinos Constantinopoulos, Michalis K. Titsias, Aristidis Likas
2002	—	`conf`	Learning About Multiple Objects in Images: Factorial Learning without Factorial Search. NIPS Christopher K. I. Williams, Michalis K. Titsias
2002	J	`jnl`	Mixture of Experts Classification Using a Hierarchical Mixture Model. Neural Comput. Michalis K. Titsias, Aristidis Likas
2001	J	`jnl`	Shared kernel models for class conditional density estimation. IEEE Trans. Neural Networks Michalis K. Titsias, Aristidis Likas
2000	—	`conf`	A Probabilistic RBF Network for Classification. IJCNN (4) Michalis K. Titsias, Aristidis Likas