79 citations · 160 across the 13 of their papers we have counts for
15 papers
Simulation-Free Learning of Population Dynamics with Wasserstein Lagrangian Residuals
Fedor Sergeev, Markus Heinonen, Daniel Waxman +4
The dynamics of cells, organisms, and fluids are often modeled as probability distributions evolving over time. Reconstructing and extrapolating this evolution from unpaired snapsh…
Wasserstein Residuals: Learning Gradient Flows from Population Dynamics
Markus Heinonen, Yair Shenfeld, Ricardo Baptista +4
Reconstructing population dynamics is a central problem in the physical and data sciences. Often, the dynamics are modeled as a Wasserstein gradient flow (WGF): a curve of distribu…
Adaptive Accompaniment with ReaLchords
Yusong Wu, Tim Cooijmans, Kyle Kastner +10
Jamming requires coordination, anticipation, and collaborative creativity between musicians. Current generative models of music produce expressive output but are not able to genera…
ReaLJam: Real-Time Human-AI Music Jamming with Reinforcement Learning-Tuned Transformers
Alexander Scarlatos, Yusong Wu, Ian Simon +5
Recent advances in generative artificial intelligence (AI) have created models capable of high-quality musical content generation. However, little consideration is given to how to…
Advantage Alignment Algorithms
Juan Agustin Duque, Milad Aghajohari, Tim Cooijmans +4
Artificially intelligent agents are increasingly being integrated into human decision-making: from large language model (LLM) assistants to autonomous vehicles. These systems often…
LOQA: Learning with Opponent Q-Learning Awareness
Milad Aghajohari, Juan Agustin Duque, Tim Cooijmans +1
In various real-world scenarios, interactions among agents often resemble the dynamics of general-sum games, where each agent strives to optimize its own utility. Despite the ubiqu…
Best Response Shaping
Milad Aghajohari, Tim Cooijmans, Juan Agustin Duque +2
We investigate the challenge of multi-agent deep reinforcement learning in partially competitive environments, where traditional methods struggle to foster reciprocity-based cooper…
Meta-Value Learning: a General Framework for Learning with Learning Awareness
Tim Cooijmans, Milad Aghajohari, Aaron Courville
Gradient-based learning in multi-agent systems is difficult because the gradient derives from a first-order model which does not account for the interaction between agents' learnin…
MIDI-DDSP: Detailed Control of Musical Performance via Hierarchical Modeling
Yusong Wu, Ethan Manilow, Yi Deng +6
Musical expression requires control of both what notes are played, and how they are performed. Conventional audio synthesizers provide detailed expressive controls, but at the cost…
Counterpoint by Convolution
Cheng-Zhi Anna Huang, Tim Cooijmans, Adam Roberts +2
Machine learning models of music typically break up the task of composition into a chronological process, composing a piece of music in a single pass from beginning to end. On the…
On the Variance of Unbiased Online Recurrent Optimization
Tim Cooijmans, James Martens
The recently proposed Unbiased Online Recurrent Optimization algorithm (UORO, arXiv:1702.05043) uses an unbiased approximation of RTRL to achieve fully online gradient-based learni…
Harmonic Recomposition using Conditional Autoregressive Modeling
Kyle Kastner, Rithesh Kumar, Tim Cooijmans +1
We demonstrate a conditional autoregressive pipeline for efficient music recomposition, based on methods presented in van den Oord et al.(2017). Recomposition (Casal & Casey, 2010)…
Theano: A Python framework for fast computation of mathematical expressions
The Theano Development Team, Rami Al-Rfou, Guillaume Alain +110
Theano is a Python library that allows to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently. Since its introduction, it has bee…
Recurrent Batch Normalization
Tim Cooijmans, Nicolas Ballas, César Laurent +2
We propose a reparameterization of LSTM that brings the benefits of batch normalization to recurrent neural networks. Whereas previous works only apply batch normalization to the i…
Dynamic Capacity Networks
Amjad Almahairi, Nicolas Ballas, Tim Cooijmans +3
We introduce the Dynamic Capacity Network (DCN), a neural network that can adaptively assign its capacity across different portions of the input data. This is achieved by combining…