Aleksandar Botev

27 papers A* 7A 1B 2Journal 14Unranked 2

Year	Rank	Type	Title / Venue / Authors
2024	J	`jnl`	Applications of flow models to the generation of correlated lattice QCD ensembles. CoRR Ryan Abbott, Aleksandar Botev, Denis Boyda, Daniel C. Hackett, Gurtej Kanwar, Sébastien Racanière, Danilo J. Rezende, Fernando Romero-López, Phiala E. Shanahan, Julian M. Urban
2024	J	`jnl`	Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models. CoRR Soham De, Samuel L. Smith, Anushan Fernando, Aleksandar Botev, George-Cristian Muraru, Albert Gu, Ruba Haroun, Leonard Berrada, Yutian Chen, Srivatsan Srinivasan, Guillaume Desjardins, Arnaud Doucet, David Budden, Yee Whye Teh, Razvan Pascanu, Nando de Freitas, Caglar Gulcehre
2024	J	`jnl`	RecurrentGemma: Moving Past Transformers for Efficient Open Language Models. CoRR Aleksandar Botev, Soham De, Samuel L. Smith, Anushan Fernando, George-Cristian Muraru, Ruba Haroun, Leonard Berrada, Razvan Pascanu, Pier Giuseppe Sessa, Robert Dadashi, Léonard Hussenot, Johan Ferret, Sertan Girgin, Olivier Bachem, Alek Andreev, Kathleen Kenealy, Thomas Mesnard, Cassidy Hardin, Surya Bhupatiraju, Shreya Pathak, Laurent Sifre, Morgane Rivière, Mihir Sanjay Kale, Juliette Love, Pouya Tafti, Armand Joulin, Noah Fiedel, Evan Senter, Yutian Chen, Srivatsan Srinivasan, Guillaume Desjardins, David Budden, Arnaud Doucet, Sharad Vikram, Adam Paszke, Trevor Gale, Sebastian Borgeaud, Charlie Chen, Andy Brock, Antonia Paterson, Jenny Brennan, Meg Risdal, Raj Gundluru, Nesh Devanathan, Paul Mooney, Nilay Chauhan, Phil Culliton, Luiz Gustavo Martins, Elisa Bandy, David Huntsperger, Glenn Cameron, Arthur Zucker, Tris Warkentin, Ludovic Peran, Minh Giang, Zoubin Ghahramani, Clément Farabet, Koray Kavukcuoglu, Demis Hassabis, Raia Hadsell, Yee Whye Teh, Nando de Frietas
2023	A*	`conf`	Deep Transformers without Shortcuts: Modifying Self-attention for Faithful Signal Propagation. ICLR Bobby He, James Martens, Guodong Zhang, Aleksandar Botev, Andrew Brock, Samuel L. Smith, Yee Whye Teh
2023	J	`jnl`	Deep Transformers without Shortcuts: Modifying Self-attention for Faithful Signal Propagation. CoRR Bobby He, James Martens, Guodong Zhang, Aleksandar Botev, Andrew Brock, Samuel L. Smith, Yee Whye Teh
2023	J	`jnl`	Normalizing flows for lattice gauge theory in arbitrary space-time dimension. CoRR Ryan Abbott, Michael S. Albergo, Aleksandar Botev, Denis Boyda, Kyle Cranmer, Daniel C. Hackett, Gurtej Kanwar, Alexander G. de G. Matthews, Sébastien Racanière, Ali Razavi, Danilo J. Rezende, Fernando Romero-López, Phiala E. Shanahan, Julian M. Urban
2022	J	`jnl`	Aspects of scaling and scalability for flow-based sampling of lattice QCD. CoRR Ryan Abbott, Michael S. Albergo, Aleksandar Botev, Denis Boyda, Kyle Cranmer, Daniel C. Hackett, Alexander G. de G. Matthews, Sébastien Racanière, Ali Razavi, Danilo J. Rezende, Fernando Romero-López, Phiala E. Shanahan, Julian M. Urban
2022	A*	`conf`	Deep Learning without Shortcuts: Shaping the Kernel with Tailored Rectifiers. ICLR Guodong Zhang, Aleksandar Botev, James Martens
2022	J	`jnl`	Deep Learning without Shortcuts: Shaping the Kernel with Tailored Rectifiers. CoRR Guodong Zhang, Aleksandar Botev, James Martens
2021	A*	`conf`	SyMetric: Measuring the Quality of Learnt Hamiltonian Dynamics Inferred from Vision. NeurIPS Irina Higgins, Peter Wirnsberger, Andrew Jaegle, Aleksandar Botev
2021	J	`jnl`	SyMetric: Measuring the Quality of Learnt Hamiltonian Dynamics Inferred from Vision. CoRR Irina Higgins, Peter Wirnsberger, Andrew Jaegle, Aleksandar Botev
2021	—	`conf`	Which priors matter? Benchmarking models for learning latent dynamics. NeurIPS Datasets and Benchmarks Aleksandar Botev, Andrew Jaegle, Peter Wirnsberger, Daniel Hennes, Irina Higgins
2021	J	`jnl`	Which priors matter? Benchmarking models for learning latent dynamics. CoRR Aleksandar Botev, Andrew Jaegle, Peter Wirnsberger, Daniel Hennes, Irina Higgins
2020	J	`jnl`	Better, Faster Fermionic Neural Networks. CoRR James S. Spencer, David Pfau, Aleksandar Botev, W. Matthew C. Foulkes
2020	A*	`conf`	Disentangling by Subspace Diffusion. NeurIPS David Pfau, Irina Higgins, Aleksandar Botev, Sébastien Racanière
2020	J	`jnl`	Disentangling by Subspace Diffusion. CoRR David Pfau, Irina Higgins, Aleksandar Botev, Sébastien Racanière
2020	A*	`conf`	Hamiltonian Generative Networks. ICLR Peter Toth, Danilo J. Rezende, Andrew Jaegle, Sébastien Racanière, Aleksandar Botev, Irina Higgins
2020	—	`—`	The Gauss-Newton matrix for Deep Learning models and its applications. Aleksandar Botev
2019	J	`jnl`	Hamiltonian Generative Networks. CoRR Peter Toth, Danilo Jimenez Rezende, Andrew Jaegle, Sébastien Racanière, Aleksandar Botev, Irina Higgins
2018	—	`conf`	A Scalable Laplace Approximation for Neural Networks. ICLR (Poster) Hippolyt Ritter, Aleksandar Botev, David Barber
2018	J	`jnl`	Online Structured Laplace Approximations For Overcoming Catastrophic Forgetting. CoRR Hippolyt Ritter, Aleksandar Botev, David Barber
2018	A*	`conf`	Online Structured Laplace Approximations for Overcoming Catastrophic Forgetting. NeurIPS Hippolyt Ritter, Aleksandar Botev, David Barber
2017	A	`conf`	Complementary Sum Sampling for Likelihood Approximation in Large Scale Classification. AISTATS Aleksandar Botev, Bowen Zheng, David Barber
2017	B	`conf`	Nesterov's accelerated gradient and momentum as approximations to regularised update descent. IJCNN Aleksandar Botev, Guy Lever, David Barber
2017	B	`conf`	Overdispersed variational autoencoders. IJCNN Harshil Shah, David Barber, Aleksandar Botev
2017	A*	`conf`	Practical Gauss-Newton Optimisation for Deep Learning. ICML Aleksandar Botev, Hippolyt Ritter, David Barber
2016	J	`jnl`	Nesterov's Accelerated Gradient and Momentum as approximations to Regularised Update Descent. CoRR Aleksandar Botev, Guy Lever, David Barber