Related papers: The Copycat Perceptron: Smashing Barriers Through …
There has been a recent paradigm shift in robotics to data-driven learning for planning and control. Due to large number of experiences required for training, most of these approaches use a self-supervised paradigm: using sensors to measure…
Training robots for operation in the real world is a complex, time consuming and potentially expensive task. Despite significant success of reinforcement learning in games and simulations, research in real robot applications has not been…
In many real-world scenarios, reward signal for agents are exceedingly sparse, making it challenging to learn an effective reward function for reward shaping. To address this issue, the proposed approach in this paper performs reward…
I study a model of information acquisition and transmission in which the sender's ability to misreport her findings is limited. The sender learns covertly, so a key observation is that in equilibrium she must be deterred from undetectably…
In this paper, we propose a novel method for enhancing security in privacy-preserving federated learning using the Vision Transformer. In federated learning, learning is performed by collecting updated information without collecting raw…
Much of human learning and inference can be framed within the computational problem of relational generalization. In this project, we propose a Bayesian model that generalizes relational knowledge to novel environments by analogically…
Near-term quantum devices can be used to build quantum machine learning models, such as quantum kernel methods and quantum neural networks (QNN) to perform classification tasks. There have been many proposals how to use variational quantum…
A key challenge in Imitation Learning (IL) is that optimal state actions demonstrations are difficult for the teacher to provide. For example in robotics, providing kinesthetic demonstrations on a robotic manipulator requires the teacher to…
In the pursuit of finding an optimal policy, reinforcement learning (RL) methods generally ignore the properties of learned policies apart from their expected return. Thus, even when successful, it is difficult to characterize which…
We present Catalyst.RL, an open-source PyTorch framework for reproducible and sample efficient reinforcement learning (RL) research. Main features of Catalyst.RL include large-scale asynchronous distributed training, efficient…
We study social learning from multiple experts whose precision is unknown and who care about reputation. The observer both learns a persistent state and ranks experts. In a binary baseline we characterize per-period equilibria: high types…
For three decades statistical mechanics has been providing a framework to analyse neural networks. However, the theoretically tractable models, e.g., perceptrons, random features models and kernel machines, or multi-index models and…
Imitation learning, which enables robots to learn behaviors from demonstrations by human, has emerged as a promising solution for generating robot motions in such environments. The imitation learning-based robot motion generation method,…
We study learning under a two-step contrastive example oracle, as introduced by Mansouri et. al. (2025), where each queried (or sampled) labeled example is paired with an additional contrastive example of opposite label. While Mansouri et…
Time-series representation learning can extract representations from data with temporal dynamics and sparse labels. When labeled data are sparse but unlabeled data are abundant, contrastive learning, i.e., a framework to learn a latent…
The teacher-student (T/S) learning has been shown to be effective for a variety of problems such as domain adaptation and model compression. One shortcoming of the T/S learning is that a teacher model, not always perfect, sporadically…
Gradient-based meta-learning algorithms have gained popularity for their ability to train models on new tasks using limited data. Empirical observations indicate that such algorithms are able to learn a shared representation across tasks,…
We study the statistical physics of the classical Ising model in the so-called $\alpha$-R\'enyi ensemble, a finite-temperature thermal state approximation that minimizes a modified free energy based on the $\alpha$-R\'enyi entropy. We begin…
We consider the problem of jointly training structured models for extraction from sources whose instances enjoy partial overlap. This has important applications like user-driven ad-hoc information extraction on the web. Such applications…
The replica method is applied to a neural network model with state-dependent synapses built from those patterns having a correlation with the state of the system greater than a certain threshold. Replica-symmetric and first-step…