To address the increasing computational demands of artificial intelligen...
Machine learning (ML) has shown great promise for revolutionizing a numb...
The main challenge of offline reinforcement learning, where data is limi...
We tackle the question of whether an agent can, by suitable choice of
pr...
We exploit a formal correspondence between thermodynamics and inference,...
We develop information-geometric techniques to analyze the trajectories ...
Denoising diffusion probabilistic models (DDPMs) are a class of powerful...
Human reconstruction and synthesis from monocular RGB videos is a challe...
We develop a technique to analyze representations learned by deep networ...
Real-world deployment of machine learning models is challenging when dat...
More data helps us generalize to a task. But real datasets can contain
o...
We develop a model of the multi-agent perimeter-defense game to calculat...
Assessing breast cancer risk from imaging remains a subjective process, ...
Despite the great promise that machine learning has offered in many fiel...
Interpretable machine learning has demonstrated impressive performance w...
What is the best way to exploit extra data – be it unlabeled data from t...
Research on both natural intelligence (NI) and artificial intelligence (...
Heterogeneity in medical data, e.g., from data collected at different si...
Leveraging data from multiple tasks, either all at once, or incrementall...
We propose a framework for deformable linear object prediction. Predicti...
Heterogeneity in medical imaging data is often tackled, in the context o...
Reliant on too many experiments to learn good actions, current Reinforce...
This paper develops a stochastic Multi-Agent Reinforcement Learning (MAR...
This paper computes a distance between tasks modeled as joint distributi...
Autonomous navigation in crowded, complex urban environments requires
in...
This paper introduces two simple techniques to improve off-policy
Reinfo...
This paper prescribes a suite of techniques for off-policy Reinforcement...
Automated machine learning (AutoML) can produce complex model ensembles ...
Learning to race autonomously is a challenging problem. It requires
perc...
We present TraDE, an attention-based architecture for auto-regressive de...
This paper employs a formal connection of machine learning with
thermody...
In many real-world applications of Machine Learning it is of paramount
i...
This paper introduces Meta-Q-Learning (MQL), a new off-policy algorithm ...
Fine-tuning a deep network trained with the standard cross-entropy loss ...
On-policy reinforcement learning (RL) algorithms have high sample comple...
Stochastic gradient descent (SGD) is widely believed to perform implicit...
We propose a new algorithm called Parle for parallel training of deep
ne...
This paper proposes a new optimization algorithm called Entropy-SGD for
...