David Balduzzi

79 papers A* 14A 7Misc 1Journal 46Unranked 11

Year	Rank	Type	Title / Venue / Authors
2022	A	`conf`	D3C: Reducing the Price of Anarchy in Multi-Agent Learning. AAMAS Ian Gemp, Kevin R. McKee, Richard Everett, Edgar A. Duéñez-Guzmán, Yoram Bachrach, David Balduzzi, Andrea Tacchetti
2021	A	`conf`	A Limited-Capacity Minimax Theorem for Non-Convex Games or: How I Learned to Stop Worrying about Mixed-Nash and Love Neural Nets. AISTATS Gauthier Gidel, David Balduzzi, Wojciech Czarnecki, Marta Garnelo, Yoram Bachrach
2021	A*	`conf`	From Poincaré Recurrence to Convergence in Imperfect Information Games: Finding Equilibrium via Regularization. ICML Julien Pérolat, Rémi Munos, Jean-Baptiste Lespiau, Shayegan Omidshafiei, Mark Rowland, Pedro A. Ortega, Neil Burch, Thomas W. Anthony, David Balduzzi, Bart De Vylder, Georgios Piliouras, Marc Lanctot, Karl Tuyls
2021	A	`conf`	Pick Your Battles: Interaction Graphs as Population-Level Objectives for Strategic Diversity. AAMAS Marta Garnelo, Wojciech Marian Czarnecki, Siqi Liu, Dhruva Tirumala, Junhyuk Oh, Gauthier Gidel, Hado van Hasselt, David Balduzzi
2021	J	`jnl`	Pick Your Battles: Interaction Graphs as Population-Level Objectives for Strategic Diversity. CoRR Marta Garnelo, Wojciech Marian Czarnecki, Siqi Liu, Dhruva Tirumala, Junhyuk Oh, Gauthier Gidel, Hado van Hasselt, David Balduzzi
2020	J	`jnl`	D3C: Reducing the Price of Anarchy in Multi-Agent Learning. CoRR Ian Gemp, Kevin R. McKee, Richard Everett, Edgar A. Duéñez-Guzmán, Yoram Bachrach, David Balduzzi, Andrea Tacchetti
2020	A*	`conf`	From Chaos to Order: Symmetry and Conservation Laws in Game Dynamics. ICML Sai Ganesh Nagarajan, David Balduzzi, Georgios Piliouras
2020	J	`jnl`	From Poincaré Recurrence to Convergence in Imperfect Information Games: Finding Equilibrium via Regularization. CoRR Julien Pérolat, Rémi Munos, Jean-Baptiste Lespiau, Shayegan Omidshafiei, Mark Rowland, Pedro A. Ortega, Neil Burch, Thomas W. Anthony, David Balduzzi, Bart De Vylder, Georgios Piliouras, Marc Lanctot, Karl Tuyls
2020	A	`conf`	Learning to Resolve Alliance Dilemmas in Many-Player Zero-Sum Games. AAMAS Edward Hughes, Thomas W. Anthony, Tom Eccles, Joel Z. Leibo, David Balduzzi, Yoram Bachrach
2020	J	`jnl`	Learning to Resolve Alliance Dilemmas in Many-Player Zero-Sum Games. CoRR Edward Hughes, Thomas W. Anthony, Tom Eccles, Joel Z. Leibo, David Balduzzi, Yoram Bachrach
2020	J	`jnl`	Minimax Theorem for Latent Games or: How I Learned to Stop Worrying about Mixed-Nash and Love Neural Nets. CoRR Gauthier Gidel, David Balduzzi, Wojciech Marian Czarnecki, Marta Garnelo, Yoram Bachrach
2020	A*	`conf`	Real World Games Look Like Spinning Tops. NeurIPS Wojciech M. Czarnecki, Gauthier Gidel, Brendan D. Tracey, Karl Tuyls, Shayegan Omidshafiei, David Balduzzi, Max Jaderberg
2020	J	`jnl`	Real World Games Look Like Spinning Tops. CoRR Wojciech Marian Czarnecki, Gauthier Gidel, Brendan D. Tracey, Karl Tuyls, Shayegan Omidshafiei, David Balduzzi, Max Jaderberg
2020	A	`conf`	Robust Self-organization in Games: Symmetries, Conservation Laws and Dimensionality Reduction. AAMAS Sai Ganesh Nagarajan, David Balduzzi, Georgios Piliouras
2020	A*	`conf`	Smooth markets: A basic mechanism for organizing gradient-based learners. ICLR David Balduzzi, Wojciech M. Czarnecki, Tom Anthony, Ian Gemp, Edward Hughes, Joel Z. Leibo, Georgios Piliouras, Thore Graepel
2020	J	`jnl`	Smooth markets: A basic mechanism for organizing gradient-based learners. CoRR David Balduzzi, Wojciech M. Czarnecki, Thomas W. Anthony, Ian M. Gemp, Edward Hughes, Joel Z. Leibo, Georgios Piliouras, Thore Graepel
2019	J	`jnl`	Differentiable Game Mechanics. CoRR Alistair Letcher, David Balduzzi, Sébastien Racanière, James Martens, Jakob N. Foerster, Karl Tuyls, Thore Graepel
2019	J	`jnl`	Differentiable Game Mechanics. J. Mach. Learn. Res. Alistair Letcher, David Balduzzi, Sébastien Racanière, James Martens, Jakob N. Foerster, Karl Tuyls, Thore Graepel
2019	J	`jnl`	LOGAN: Latent Optimisation for Generative Adversarial Networks. CoRR Yan Wu, Jeff Donahue, David Balduzzi, Karen Simonyan, Timothy P. Lillicrap
2019	J	`jnl`	Open-ended Learning in Symmetric Zero-sum Games. CoRR David Balduzzi, Marta Garnelo, Yoram Bachrach, Wojciech M. Czarnecki, Julien Pérolat, Max Jaderberg, Thore Graepel
2019	A*	`conf`	Open-ended learning in symmetric zero-sum games. ICML David Balduzzi, Marta Garnelo, Yoram Bachrach, Wojciech Czarnecki, Julien Pérolat, Max Jaderberg, Thore Graepel
2019	—	`conf`	Stable Opponent Shaping in Differentiable Games. ICLR (Poster) Alistair Letcher, Jakob N. Foerster, David Balduzzi, Tim Rocktäschel, Shimon Whiteson
2018	A*	`conf`	Re-evaluating evaluation. NeurIPS David Balduzzi, Karl Tuyls, Julien Pérolat, Thore Graepel
2018	J	`jnl`	Re-evaluating evaluation. CoRR David Balduzzi, Karl Tuyls, Julien Pérolat, Thore Graepel
2018	J	`jnl`	Stable Opponent Shaping in Differentiable Games. CoRR Alistair Letcher, Jakob N. Foerster, David Balduzzi, Tim Rocktäschel, Shimon Whiteson
2018	A*	`conf`	The Mechanics of n-Player Differentiable Games. ICML David Balduzzi, Sébastien Racanière, James Martens, Jakob N. Foerster, Karl Tuyls, Thore Graepel
2018	J	`jnl`	The Mechanics of n-Player Differentiable Games. CoRR David Balduzzi, Sébastien Racanière, James Martens, Jakob N. Foerster, Karl Tuyls, Thore Graepel
2017	Misc	`conf`	Back To RGB: Deep articulated hand pose estimation from a single camera image. IVCNZ Kurt Wan-Duo Ma, J. P. Lewis, Marcus Frean, David Balduzzi
2017	A*	`conf`	Neural Taylor Approximations: Convergence and Exploration in Rectifier Networks. ICML David Balduzzi, Brian McWilliams, Tony Butler-Yeoman
2017	J	`jnl`	Scatter Component Analysis: A Unified Framework for Domain Adaptation and Domain Generalization. IEEE Trans. Pattern Anal. Mach. Intell. Muhammad Ghifary, David Balduzzi, W. Bastiaan Kleijn, Mengjie Zhang
2017	A*	`conf`	Strongly-Typed Agents are Guaranteed to Interact Safely. ICML David Balduzzi
2017	J	`jnl`	Strongly-Typed Agents are Guaranteed to Interact Safely. CoRR David Balduzzi
2017	A*	`conf`	The Shattered Gradients Problem: If resnets are the answer, then what is the question? ICML David Balduzzi, Marcus Frean, Lennox Leary, J. P. Lewis, Kurt Wan-Duo Ma, Brian McWilliams
2017	J	`jnl`	The Shattered Gradients Problem: If resnets are the answer, then what is the question? CoRR David Balduzzi, Marcus Frean, Lennox Leary, J. P. Lewis, Kurt Wan-Duo Ma, Brian McWilliams
2016	J	`jnl`	Compliance-Aware Bandits. CoRR Nicolás Della Penna, Mark D. Reid, David Balduzzi
2016	J	`jnl`	Deep Online Convex Optimization with Gated Games. CoRR David Balduzzi
2016	—	`conf`	Deep Reconstruction-Classification Networks for Unsupervised Domain Adaptation. ECCV (4) Muhammad Ghifary, W. Bastiaan Kleijn, Mengjie Zhang, David Balduzzi, Wen Li
2016	J	`jnl`	Deep Reconstruction-Classification Networks for Unsupervised Domain Adaptation. CoRR Muhammad Ghifary, W. Bastiaan Kleijn, Mengjie Zhang, David Balduzzi, Wen Li
2016	J	`jnl`	Neural Taylor Approximations: Convergence and Exploration in Rectifier Networks. CoRR David Balduzzi, Brian McWilliams, Tony Butler-Yeoman
2016	A*	`conf`	Strongly-Typed Recurrent Neural Networks. ICML David Balduzzi, Muhammad Ghifary
2016	J	`jnl`	Strongly-Typed Recurrent Neural Networks. CoRR David Balduzzi, Muhammad Ghifary
2015	J	`jnl`	Compatible Value Gradients for Reinforcement Learning of Continuous Deep Policies. CoRR David Balduzzi, Muhammad Ghifary
2015	A*	`conf`	Domain Generalization for Object Recognition with Multi-task Autoencoders. ICCV Muhammad Ghifary, W. Bastiaan Kleijn, Mengjie Zhang, David Balduzzi
2015	J	`jnl`	Domain Generalization for Object Recognition with Multi-task Autoencoders. CoRR Muhammad Ghifary, W. Bastiaan Kleijn, Mengjie Zhang, David Balduzzi
2015	J	`jnl`	Grammars for Games: A Gradient-Based, Game-Theoretic Framework for Optimization in Deep Learning. Frontiers Robotics AI David Balduzzi
2015	A*	`conf`	Kickback Cuts Backprop's Red-Tape: Biologically Plausible Credit Assignment in Neural Networks. AAAI David Balduzzi, Hastagiri Vanchinathan, Joachim M. Buhmann
2015	A	`conf`	Learning the Structure of Sum-Product Networks via an SVD-based Algorithm. UAI Tameem Adel, David Balduzzi, Ali Ghodsi
2015	J	`jnl`	Scatter Component Analysis: A Unified Framework for Domain Adaptation and Domain Generalization. CoRR Muhammad Ghifary, David Balduzzi, W. Bastiaan Kleijn, Mengjie Zhang
2015	J	`jnl`	Semantics, Representations and Grammars for Deep Learning. CoRR David Balduzzi
2014	A	`conf`	Cortical prediction markets. AAMAS David Balduzzi
2014	J	`jnl`	Cortical prediction markets. CoRR David Balduzzi
2014	J	`jnl`	Falsifiable implies Learnable. CoRR David Balduzzi
2014	J	`jnl`	Kickback cuts Backprop's red-tape: Biologically plausible credit assignment in neural networks. CoRR David Balduzzi, Hastagiri Vanchinathan, Joachim M. Buhmann
2014	J	`jnl`	Uncovering the structure and temporal dynamics of information propagation. Netw. Sci. Manuel Gomez-Rodriguez, Jure Leskovec, David Balduzzi, Bernhard Schölkopf
2013	—	`conf`	Correlated random features for fast semi-supervised learning. NIPS Brian McWilliams, David Balduzzi, Joachim M. Buhmann
2013	J	`jnl`	Correlated random features for fast semi-supervised learning. CoRR Brian McWilliams, David Balduzzi, Joachim M. Buhmann
2013	J	`jnl`	Domain Generalization via Invariant Feature Representation CoRR Krikamol Muandet, David Balduzzi, Bernhard Schölkopf
2013	—	`conf`	Domain Generalization via Invariant Feature Representation. ICML (1) Krikamol Muandet, David Balduzzi, Bernhard Schölkopf
2013	J	`jnl`	Metabolic Cost as an Organizing Principle for Cooperative Learning. Adv. Complex Syst. David Balduzzi, Pedro A. Ortega, Michel Besserve
2013	J	`jnl`	Randomized co-training: from cortical neurons to machine learning and back again. CoRR David Balduzzi
2013	J	`jnl`	What can neurons do for their brain? Communicate selectivity with bursts. Theory Biosci. David Balduzzi, Giulio Tononi
2012	J	`jnl`	A Nonparametric Conjugate Prior Distribution for the Maximizing Argument of a Noisy Function CoRR Pedro A. Ortega, Jordi Grau-Moya, Tim Genewein, David Balduzzi, Daniel A. Braun
2012	—	`conf`	A Nonparametric Conjugate Prior Distribution for the Maximizing Argument of a Noisy Function. NIPS Pedro A. Ortega, Jordi Grau-Moya, Tim Genewein, David Balduzzi, Daniel A. Braun
2012	J	`jnl`	Metabolic cost as an organizing principle for cooperative learning CoRR David Balduzzi, Pedro A. Ortega, Michel Besserve
2012	J	`jnl`	Regulating the information in spikes: a useful bias CoRR David Balduzzi
2012	J	`jnl`	Towards a learning-theoretic analysis of spike-timing dependent plasticity CoRR David Balduzzi, Michel Besserve
2012	—	`conf`	Towards a learning-theoretic analysis of spike-timing dependent plasticity. NIPS David Balduzzi, Michel Besserve
2011	J	`jnl`	Detecting emergent processes in cellular automata with excess information CoRR David Balduzzi
2011	—	`conf`	Detecting emergent processes in cellular automata with excess information. ECAL David Balduzzi
2011	—	`conf`	Estimating integrated information with TMS pulses during wakefulness, sleep, and under anesthesia. EMBC David Balduzzi
2011	—	`conf`	Falsification and Future Performance. Algorithmic Probability and Friends David Balduzzi
2011	J	`jnl`	Falsification and future performance CoRR David Balduzzi
2011	J	`jnl`	Information, learning and falsification CoRR David Balduzzi
2011	—	`conf`	On the information-theoretic structure of distributed measurements DCM David Balduzzi
2011	J	`jnl`	Uncovering the Temporal Dynamics of Diffusion Networks CoRR Manuel Gomez-Rodriguez, David Balduzzi, Bernhard Schölkopf
2011	A*	`conf`	Uncovering the Temporal Dynamics of Diffusion Networks. ICML Manuel Gomez-Rodriguez, David Balduzzi, Bernhard Schölkopf
2009	J	`jnl`	Qualia: The Geometry of Integrated Information. PLoS Comput. Biol. David Balduzzi, Giulio Tononi
2008	J	`jnl`	Integrated Information in Discrete Dynamical Systems: Motivation and Theoretical Framework. PLoS Comput. Biol. David Balduzzi, Giulio Tononi
2007	—	`conf`	Measuring Consciousness as Integrated Information. AAAI Fall Symposium: AI and Consciousness Giulio Tononi, David Balduzzi