papers

Publications (43)

cs.LG2014

Falsifiable implies Learnable

David Balduzzi

The paper demonstrates that falsifiability is fundamental to learning. We prove the following theorem for statistical learning and sequential prediction: If a theory is falsifiable…

cs.LG2020

Smooth markets: A basic mechanism for organizing gradient-based learners

David Balduzzi, Wojciech M Czarnecki, Thomas W Anthony +5

With the success of modern machine learning, it is becoming increasingly important to understand and control how learning algorithms interact. Unfortunately, negative results from…

stat.ML2013

Correlated random features for fast semi-supervised learning

Brian McWilliams, David Balduzzi, Joachim M. Buhmann

This paper presents Correlated Nystrom Views (XNV), a fast semi-supervised algorithm for regression and classification. The algorithm draws on two main ideas. First, it generates t…

cs.AI2014

Cortical prediction markets

David Balduzzi

We investigate cortical learning from the perspective of mechanism design. First, we show that discretizing standard models of neurons and synaptic plasticity leads to rational age…

cs.LG2018

Strongly-Typed Agents are Guaranteed to Interact Safely

David Balduzzi

As artificial agents proliferate, it is becoming increasingly important to ensure that their interactions with one another are well-behaved. In this paper, we formalize a common-se…

cs.LG2018

Neural Taylor Approximations: Convergence and Exploration in Rectifier Networks

David Balduzzi, Brian McWilliams, Tony Butler-Yeoman

Modern convolutional networks, incorporating rectifiers and max-pooling, are neither smooth nor convex; standard guarantees therefore do not apply. Nevertheless, methods from conve…

cs.LG2016

Deep Online Convex Optimization with Gated Games

David Balduzzi

Methods from convex optimization are widely used as building blocks for deep learning algorithms. However, the reasons for their empirical success are unclear, since modern convolu…

cs.CV2015

Domain Generalization for Object Recognition with Multi-task Autoencoders

Muhammad Ghifary, W. Bastiaan Kleijn, Mengjie Zhang +1

The problem of domain generalization is to take knowledge acquired from a number of related domains where training data is available, and to then successfully apply it to previousl…

cs.LG2015

Semantics, Representations and Grammars for Deep Learning

David Balduzzi

Deep learning is currently the subject of intensive study. However, fundamental concepts such as representations are not formally defined -- researchers "know them when they see th…

cs.GT2020

From Poincaré Recurrence to Convergence in Imperfect Information Games: Finding Equilibrium via Regularization

Julien Perolat, Remi Munos, Jean-Baptiste Lespiau +10

In this paper we investigate the Follow the Regularized Leader dynamics in sequential imperfect information games (IIG). We generalize existing results of Poincaré recurrence from…

cs.LG2019

Open-ended Learning in Symmetric Zero-sum Games

David Balduzzi, Marta Garnelo, Yoram Bachrach +4

Zero-sum games such as chess and poker are, abstractly, functions that evaluate pairs of agents, for example labeling them `winner' and `loser'. If the game is approximately transi…

cs.LG2014

Kickback cuts Backprop's red-tape: Biologically plausible credit assignment in neural networks

David Balduzzi, Hastagiri Vanchinathan, Joachim Buhmann

Error backpropagation is an extremely effective algorithm for assigning credit in artificial neural networks. However, weight updates under Backprop depend on lengthy recursive com…

cs.MA2021

Stable Opponent Shaping in Differentiable Games

Alistair Letcher, Jakob Foerster, David Balduzzi +2

A growing number of learning methods are actually differentiable games whose players optimise multiple, interdependent objectives in parallel -- from GANs and intrinsic curiosity t…

stat.ML2013

Domain Generalization via Invariant Feature Representation

Krikamol Muandet, David Balduzzi, Bernhard Schölkopf

This paper investigates domain generalization: How to take knowledge acquired from an arbitrary number of related domains and apply it to previously unseen domains? We propose Doma…

cs.LG2013

Randomized co-training: from cortical neurons to machine learning and back again

David Balduzzi

Despite its size and complexity, the human cortex exhibits striking anatomical regularities, suggesting there may simple meta-algorithms underlying cortical learning and computatio…

q-bio.NC2012

Towards a learning-theoretic analysis of spike-timing dependent plasticity

David Balduzzi, Michel Besserve

This paper suggests a learning-theoretic perspective on how synaptic plasticity benefits global brain functioning. We introduce a model, the selectron, that (i) arises as the fast…

cs.AI2021

Pick Your Battles: Interaction Graphs as Population-Level Objectives for Strategic Diversity

Marta Garnelo, Wojciech Marian Czarnecki, Siqi Liu +5

Strategic diversity is often essential in games: in multi-player games, for example, evaluating a player against a diverse set of strategies will yield a more accurate estimate of…

cs.IT2012

On the information-theoretic structure of distributed measurements

David Balduzzi

The internal structure of a measuring device, which depends on what its components are and how they are organized, determines how it categorizes its inputs. This paper presents a g…

stat.ML2012

A Nonparametric Conjugate Prior Distribution for the Maximizing Argument of a Noisy Function

Pedro A. Ortega, Jordi Grau-Moya, Tim Genewein +2

We propose a novel Bayesian approach to solve stochastic optimization problems that involve finding extrema of noisy, nonlinear functions. Previous work has focused on representing…

cs.CV2016

Deep Reconstruction-Classification Networks for Unsupervised Domain Adaptation

Muhammad Ghifary, W. Bastiaan Kleijn, Mengjie Zhang +2

In this paper, we propose a novel unsupervised domain adaptation algorithm based on deep learning for visual object recognition. Specifically, we design a new model called Deep Rec…

cs.LG2019

Differentiable Game Mechanics

Alistair Letcher, David Balduzzi, Sebastien Racaniere +4

Deep learning is built on the foundational guarantee that gradient descent on an objective function converges to local minima. Unfortunately, this guarantee fails in settings, such…

cs.LG2016

Deep Online Convex Optimization by Putting Forecaster to Sleep

David Balduzzi

Methods from convex optimization such as accelerated gradient descent are widely used as building blocks for deep learning algorithms. However, the reasons for their empirical succ…

stat.ML2011

Falsification and future performance

David Balduzzi

We information-theoretically reformulate two measures of capacity from statistical learning theory: empirical VC-entropy and empirical Rademacher complexity. We show these capacity…

cs.LG2018

The Mechanics of n-Player Differentiable Games

David Balduzzi, Sebastien Racaniere, James Martens +3

The cornerstone underpinning deep learning is the guarantee that gradient descent on an objective converges to local minima. Unfortunately, this guarantee fails in settings, such a…

cs.LG2016

Strongly-Typed Recurrent Neural Networks

David Balduzzi, Muhammad Ghifary

Recurrent neural networks are increasing popular models for sequential learning. Unfortunately, although the most effective RNN architectures are perhaps excessively complicated, e…

math.ST2014

Quantifying causal influences

Dominik Janzing, David Balduzzi, Moritz Grosse-Wentrup +1

Many methods for causal inference generate directed acyclic graphs (DAGs) that formalize causal relations between variables. Given the joint distribution on all these variables…

cs.IT2011

Information, learning and falsification

David Balduzzi

There are (at least) three approaches to quantifying information. The first, algorithmic information or Kolmogorov complexity, takes events as strings and, given a universal Turing…

math.AG2006

Donagi-Markman cubic for Hitchin systems

David Balduzzi

The Donagi-Markman cubic is the differential of the period map for algebraic completely integrable systems. Here we prove a formula for the cubic in the case of Hitchin's system fo…

cs.IT2011

Detecting emergent processes in cellular automata with excess information

David Balduzzi

Many natural processes occur over characteristic spatial and temporal scales. This paper presents tools for (i) flexibly and scalably coarse-graining cellular automata and (ii) ide…

math.AG2007

Poisson geometry of parabolic bundles on Elliptic curves

David Balduzzi

The moduli space of -bundles on an elliptic curve with additional flag structure admits a Poisson structure. The bivector can be defined using double loop group, loop group and…

stat.ML2016

Compliance-Aware Bandits

Nicolás Della Penna, Mark D. Reid, David Balduzzi

Motivated by clinical trials, we study bandits with observable non-compliance. At each step, the learner chooses an arm, after, instead of observing only the reward, it also observ…

cs.LG2020

Real World Games Look Like Spinning Tops

Wojciech Marian Czarnecki, Gauthier Gidel, Brendan Tracey +4

This paper investigates the geometrical properties of real world games (e.g. Tic-Tac-Toe, Go, StarCraft II). We hypothesise that their geometrical structure resemble a spinning top…

cs.CV2016

Scatter Component Analysis: A Unified Framework for Domain Adaptation and Domain Generalization

Muhammad Ghifary, David Balduzzi, W. Bastiaan Kleijn +1

This paper addresses classification tasks on a particular target domain in which labeled training data are only available from source domains different from (but related to) the ta…

q-bio.NC2013

Metabolic cost as an organizing principle for cooperative learning

David Balduzzi, Pedro A Ortega, Michel Besserve

This paper investigates how neurons can use metabolic cost to facilitate learning at a population level. Although decision-making by individual neurons has been extensively studied…

cs.SI2011

Uncovering the Temporal Dynamics of Diffusion Networks

Manuel Gomez Rodriguez, David Balduzzi, Bernhard Schölkopf

Time plays an essential role in the diffusion of information, influence and disease over networks. In many cases we only observe when a node copies information, makes a decision or…

cs.GT2020

Learning to Resolve Alliance Dilemmas in Many-Player Zero-Sum Games

Edward Hughes, Thomas W. Anthony, Tom Eccles +3

Zero-sum games have long guided artificial intelligence research, since they possess both a rich strategy space of best-responses and a clear evaluation metric. What's more, compet…

stat.ML2021

A Limited-Capacity Minimax Theorem for Non-Convex Games or: How I Learned to Stop Worrying about Mixed-Nash and Love Neural Nets

Gauthier Gidel, David Balduzzi, Wojciech Marian Czarnecki +2

Adversarial training, a special case of multi-objective optimization, is an increasingly prevalent machine learning technique: some of its most notable applications include GAN-bas…

cs.MA2022

D3C: Reducing the Price of Anarchy in Multi-Agent Learning

Ian Gemp, Kevin R. McKee, Richard Everett +4

In multiagent systems, the complex interaction of fixed incentives can lead agents to outcomes that are poor (inefficient) not only for the group, but also for each individual. Pri…

cs.LG2020

LOGAN: Latent Optimisation for Generative Adversarial Networks

Yan Wu, Jeff Donahue, David Balduzzi +2

Training generative adversarial networks requires balancing of delicate adversarial dynamics. Even with careful tuning, training may diverge or end up in a bad equilibrium with dro…

cs.NE2018

The Shattered Gradients Problem: If resnets are the answer, then what is the question?

David Balduzzi, Marcus Frean, Lennox Leary +3

A long-standing obstacle to progress in deep learning is the problem of vanishing and exploding gradients. Although, the problem has largely been overcome via carefully constructed…

cs.LG2015

Compatible Value Gradients for Reinforcement Learning of Continuous Deep Policies

David Balduzzi, Muhammad Ghifary

This paper proposes GProp, a deep reinforcement learning algorithm for continuous policies with compatible function approximation. The algorithm is based on two innovations. Firstl…

q-bio.NC2012

Regulating the information in spikes: a useful bias

David Balduzzi

The bias/variance tradeoff is fundamental to learning: increasing a model's complexity can improve its fit on training data, but potentially worsens performance on future samples.…

cs.LG2018

Re-evaluating Evaluation

David Balduzzi, Karl Tuyls, Julien Perolat +1

Progress in machine learning is measured by careful evaluation on problems of outstanding common interest. However, the proliferation of benchmark suites and environments, adversar…