David Balduzzi

Publication Activity (10 Years)

Years Active: 2007-2022
Publications (10 Years): 49

Top Topics

Imperfect Information

Conservation Laws

Top Venues

Publications

Ian M. Gemp, Kevin R. McKee, Richard Everett, Edgar A. Duéñez-Guzmán, Yoram Bachrach, David Balduzzi, Andrea Tacchetti
D3C: Reducing the Price of Anarchy in Multi-Agent Learning. AAMAS (2022)
Marta Garnelo, Wojciech Marian Czarnecki, Siqi Liu, Dhruva Tirumala, Junhyuk Oh, Gauthier Gidel, Hado van Hasselt, David Balduzzi
Pick Your Battles: Interaction Graphs as Population-Level Objectives for Strategic Diversity. CoRR (2021)
Marta Garnelo, Wojciech Marian Czarnecki, Siqi Liu, Dhruva Tirumala, Junhyuk Oh, Gauthier Gidel, Hado van Hasselt, David Balduzzi
Pick Your Battles: Interaction Graphs as Population-Level Objectives for Strategic Diversity. AAMAS (2021)
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
From Poincaré Recurrence to Convergence in Imperfect Information Games: Finding Equilibrium via Regularization. ICML (2021)
Gauthier Gidel, David Balduzzi, Wojciech Czarnecki, Marta Garnelo, Yoram Bachrach
A Limited-Capacity Minimax Theorem for Non-Convex Games or: How I Learned to Stop Worrying about Mixed-Nash and Love Neural Nets. AISTATS (2021)
Ian M. Gemp, Kevin R. McKee, Richard Everett, Edgar A. Duéñez-Guzmán, Yoram Bachrach, David Balduzzi, Andrea Tacchetti
D3C: Reducing the Price of Anarchy in Multi-Agent Learning. CoRR (2020)
Gauthier Gidel, David Balduzzi, Wojciech Marian Czarnecki, Marta Garnelo, Yoram Bachrach
Minimax Theorem for Latent Games or: How I Learned to Stop Worrying about Mixed-Nash and Love Neural Nets. CoRR (2020)
David Balduzzi, Wojciech M. Czarnecki, Tom Anthony, Ian M. Gemp, Edward Hughes, Joel Z. Leibo, Georgios Piliouras, Thore Graepel
Smooth markets: A basic mechanism for organizing gradient-based learners. ICLR (2020)
David Balduzzi, Wojciech M. Czarnecki, Thomas W. Anthony, Ian M. Gemp, Edward Hughes, Joel Z. Leibo, Georgios Piliouras, Thore Graepel
Smooth markets: A basic mechanism for organizing gradient-based learners. CoRR (2020)
Wojciech M. Czarnecki, Gauthier Gidel, Brendan D. Tracey, Karl Tuyls, Shayegan Omidshafiei, David Balduzzi, Max Jaderberg
Real World Games Look Like Spinning Tops. NeurIPS (2020)
Edward Hughes, Thomas W. Anthony, Tom Eccles, Joel Z. Leibo, David Balduzzi, Yoram Bachrach
Learning to Resolve Alliance Dilemmas in Many-Player Zero-Sum Games. AAMAS (2020)
Sai Ganesh Nagarajan, David Balduzzi, Georgios Piliouras
From Chaos to Order: Symmetry and Conservation Laws in Game Dynamics. ICML (2020)
Edward Hughes, Thomas W. Anthony, Tom Eccles, Joel Z. Leibo, David Balduzzi, Yoram Bachrach
Learning to Resolve Alliance Dilemmas in Many-Player Zero-Sum Games. CoRR (2020)
Wojciech Marian Czarnecki, Gauthier Gidel, Brendan D. Tracey, Karl Tuyls, Shayegan Omidshafiei, David Balduzzi, Max Jaderberg
Real World Games Look Like Spinning Tops. CoRR (2020)
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
From Poincaré Recurrence to Convergence in Imperfect Information Games: Finding Equilibrium via Regularization. CoRR (2020)
Sai Ganesh Nagarajan, David Balduzzi, Georgios Piliouras
Robust Self-organization in Games: Symmetries, Conservation Laws and Dimensionality Reduction. AAMAS (2020)
David Balduzzi, Marta Garnelo, Yoram Bachrach, Wojciech M. Czarnecki, Julien Pérolat, Max Jaderberg, Thore Graepel
Open-ended Learning in Symmetric Zero-sum Games. CoRR (2019)
Alistair Letcher, David Balduzzi, Sébastien Racanière, James Martens, Jakob N. Foerster, Karl Tuyls, Thore Graepel
Differentiable Game Mechanics. J. Mach. Learn. Res. 20 (2019)
Alistair Letcher, Jakob N. Foerster, David Balduzzi, Tim Rocktäschel, Shimon Whiteson
Stable Opponent Shaping in Differentiable Games. ICLR (Poster) (2019)
Alistair Letcher, David Balduzzi, Sébastien Racanière, James Martens, Jakob N. Foerster, Karl Tuyls, Thore Graepel
Differentiable Game Mechanics. CoRR (2019)
David Balduzzi, Marta Garnelo, Yoram Bachrach, Wojciech Czarnecki, Julien Pérolat, Max Jaderberg, Thore Graepel
Open-ended learning in symmetric zero-sum games. ICML (2019)
Yan Wu, Jeff Donahue, David Balduzzi, Karen Simonyan, Timothy P. Lillicrap
LOGAN: Latent Optimisation for Generative Adversarial Networks. CoRR (2019)
David Balduzzi, Sébastien Racanière, James Martens, Jakob N. Foerster, Karl Tuyls, Thore Graepel
The Mechanics of n-Player Differentiable Games. CoRR (2018)
David Balduzzi, Karl Tuyls, Julien Pérolat, Thore Graepel
Re-evaluating evaluation. NeurIPS (2018)
David Balduzzi, Sébastien Racanière, James Martens, Jakob N. Foerster, Karl Tuyls, Thore Graepel
The Mechanics of n-Player Differentiable Games. ICML (2018)
Alistair Letcher, Jakob N. Foerster, David Balduzzi, Tim Rocktäschel, Shimon Whiteson
Stable Opponent Shaping in Differentiable Games. CoRR (2018)
David Balduzzi, Karl Tuyls, Julien Pérolat, Thore Graepel
Re-evaluating evaluation. CoRR (2018)
David Balduzzi, Marcus Frean, Lennox Leary, J. P. Lewis, Kurt Wan-Duo Ma, Brian McWilliams
The Shattered Gradients Problem: If resnets are the answer, then what is the question? ICML (2017)
Kurt Wan-Duo Ma, J. P. Lewis, Marcus Frean, David Balduzzi
Back To RGB: Deep articulated hand pose estimation from a single camera image. IVCNZ (2017)
David Balduzzi, Brian McWilliams, Tony Butler-Yeoman
Neural Taylor Approximations: Convergence and Exploration in Rectifier Networks. ICML (2017)
Muhammad Ghifary, David Balduzzi, W. Bastiaan Kleijn, Mengjie Zhang
Scatter Component Analysis: A Unified Framework for Domain Adaptation and Domain Generalization. IEEE Trans. Pattern Anal. Mach. Intell. 39 (7) (2017)
David Balduzzi, Marcus Frean, Lennox Leary, J. P. Lewis, Kurt Wan-Duo Ma, Brian McWilliams
The Shattered Gradients Problem: If resnets are the answer, then what is the question? CoRR (2017)
David Balduzzi
Strongly-Typed Agents are Guaranteed to Interact Safely. ICML (2017)
David Balduzzi
Strongly-Typed Agents are Guaranteed to Interact Safely. CoRR (2017)
Nicolás Della Penna, Mark D. Reid, David Balduzzi
Compliance-Aware Bandits. CoRR (2016)
Muhammad Ghifary, W. Bastiaan Kleijn, Mengjie Zhang, David Balduzzi, Wen Li
Deep Reconstruction-Classification Networks for Unsupervised Domain Adaptation. CoRR (2016)
Muhammad Ghifary, W. Bastiaan Kleijn, Mengjie Zhang, David Balduzzi, Wen Li
Deep Reconstruction-Classification Networks for Unsupervised Domain Adaptation. ECCV (4) (2016)
David Balduzzi, Muhammad Ghifary
Strongly-Typed Recurrent Neural Networks. ICML (2016)
David Balduzzi, Brian McWilliams, Tony Butler-Yeoman
Neural Taylor Approximations: Convergence and Exploration in Rectifier Networks. CoRR (2016)
David Balduzzi, Muhammad Ghifary
Strongly-Typed Recurrent Neural Networks. CoRR (2016)
David Balduzzi
Deep Online Convex Optimization with Gated Games. CoRR (2016)
David Balduzzi, Muhammad Ghifary
Compatible Value Gradients for Reinforcement Learning of Continuous Deep Policies. CoRR (2015)
David Balduzzi, Hastagiri Vanchinathan, Joachim M. Buhmann
Kickback Cuts Backprop's Red-Tape: Biologically Plausible Credit Assignment in Neural Networks. AAAI (2015)
David Balduzzi
Semantics, Representations and Grammars for Deep Learning. CoRR (2015)
Muhammad Ghifary, David Balduzzi, W. Bastiaan Kleijn, Mengjie Zhang
Scatter Component Analysis: A Unified Framework for Domain Adaptation and Domain Generalization. CoRR (2015)
David Balduzzi
Grammars for Games: A Gradient-Based, Game-Theoretic Framework for Optimization in Deep Learning. Frontiers Robotics AI 2 (2015)
Muhammad Ghifary, W. Bastiaan Kleijn, Mengjie Zhang, David Balduzzi
Domain Generalization for Object Recognition with Multi-task Autoencoders. CoRR (2015)
Muhammad Ghifary, W. Bastiaan Kleijn, Mengjie Zhang, David Balduzzi
Domain Generalization for Object Recognition with Multi-task Autoencoders. ICCV (2015)
Tameem Adel, David Balduzzi, Ali Ghodsi
Learning the Structure of Sum-Product Networks via an SVD-based Algorithm. UAI (2015)
David Balduzzi
Cortical prediction markets. AAMAS (2014)
David Balduzzi
Falsifiable implies Learnable. CoRR (2014)
David Balduzzi
Cortical prediction markets. CoRR (2014)
David Balduzzi, Hastagiri Vanchinathan, Joachim M. Buhmann
Kickback cuts Backprop's red-tape: Biologically plausible credit assignment in neural networks. CoRR (2014)
Manuel Gomez-Rodriguez, Jure Leskovec, David Balduzzi, Bernhard Schölkopf
Uncovering the structure and temporal dynamics of information propagation. Netw. Sci. 2 (1) (2014)
Brian McWilliams, David Balduzzi, Joachim M. Buhmann
Correlated random features for fast semi-supervised learning. NIPS (2013)
David Balduzzi
Randomized co-training: from cortical neurons to machine learning and back again. CoRR (2013)
David Balduzzi, Pedro A. Ortega, Michel Besserve
Metabolic Cost as an Organizing Principle for Cooperative Learning. Adv. Complex Syst. 16 (2-3) (2013)
Brian McWilliams, David Balduzzi, Joachim M. Buhmann
Correlated random features for fast semi-supervised learning. CoRR (2013)
David Balduzzi, Giulio Tononi
What can neurons do for their brain? Communicate selectivity with bursts. Theory Biosci. 132 (1) (2013)
Krikamol Muandet, David Balduzzi, Bernhard Schölkopf
Domain Generalization via Invariant Feature Representation CoRR (2013)
Krikamol Muandet, David Balduzzi, Bernhard Schölkopf
Domain Generalization via Invariant Feature Representation. ICML (1) (2013)
David Balduzzi, Michel Besserve
Towards a learning-theoretic analysis of spike-timing dependent plasticity. NIPS (2012)
David Balduzzi, Pedro A. Ortega, Michel Besserve
Metabolic cost as an organizing principle for cooperative learning CoRR (2012)
David Balduzzi, Michel Besserve
Towards a learning-theoretic analysis of spike-timing dependent plasticity CoRR (2012)
Pedro A. Ortega, Jordi Grau-Moya, Tim Genewein, David Balduzzi, Daniel A. Braun
A Nonparametric Conjugate Prior Distribution for the Maximizing Argument of a Noisy Function. NIPS (2012)
David Balduzzi
Regulating the information in spikes: a useful bias CoRR (2012)
Pedro A. Ortega, Jordi Grau-Moya, Tim Genewein, David Balduzzi, Daniel A. Braun
A Nonparametric Conjugate Prior Distribution for the Maximizing Argument of a Noisy Function CoRR (2012)
David Balduzzi
Estimating integrated information with TMS pulses during wakefulness, sleep, and under anesthesia. EMBC (2011)
David Balduzzi
Falsification and future performance CoRR (2011)
David Balduzzi
Detecting emergent processes in cellular automata with excess information CoRR (2011)
David Balduzzi
Falsification and Future Performance. Algorithmic Probability and Friends (2011)
Manuel Gomez-Rodriguez, David Balduzzi, Bernhard Schölkopf
Uncovering the Temporal Dynamics of Diffusion Networks. ICML (2011)
David Balduzzi
Information, learning and falsification CoRR (2011)
David Balduzzi
Detecting emergent processes in cellular automata with excess information. ECAL (2011)
David Balduzzi
On the information-theoretic structure of distributed measurements DCM (2011)
Manuel Gomez-Rodriguez, David Balduzzi, Bernhard Schölkopf
Uncovering the Temporal Dynamics of Diffusion Networks CoRR (2011)
David Balduzzi, Giulio Tononi
Qualia: The Geometry of Integrated Information. PLoS Comput. Biol. 5 (8) (2009)
David Balduzzi, Giulio Tononi
Integrated Information in Discrete Dynamical Systems: Motivation and Theoretical Framework. PLoS Comput. Biol. 4 (6) (2008)
Giulio Tononi, David Balduzzi
Measuring Consciousness as Integrated Information. AAAI Fall Symposium: AI and Consciousness (2007)