Related papers: Supervised Learning in the Presence of Concept Dri…
Transfer learning aims to leverage knowledge from pre-trained models to benefit the target task. Prior transfer learning work mainly transfers from a single model. However, with the emergence of deep models pre-trained from different…
Despite the widespread practical success of deep learning methods, our theoretical understanding of the dynamics of learning in deep neural networks remains quite sparse. We attempt to bridge the gap between the theory and practice of deep…
Reinforcement Learning (RL) consists of designing agents that make intelligent decisions without human supervision. When used alongside function approximators such as Neural Networks (NNs), RL is capable of solving extremely complex…
This research proposes a novel drift detection methodology for machine learning (ML) models based on the concept of ''deformation'' in the vector space representation of data. Recognizing that new data can act as forces stretching,…
A semi-parametric, non-linear regression model in the presence of latent variables is applied towards learning network graph structure. These latent variables can correspond to unmodeled phenomena or unmeasured agents in a complex system of…
Adaptive learning technology solutions often use a learner model to trace learning and make pedagogical decisions. The present research introduces a formalized methodology for specifying learner models, Logistic Knowledge Tracing (LKT),…
Concept drift is a major problem in online learning due to its impact on the predictive performance of data stream mining systems. Recent studies have started exploring data streams from different sources as a strategy to tackle concept…
A key property of neural networks (both biological and artificial) is how they learn to represent and manipulate input information in order to solve a task. Different types of representations may be suited to different types of tasks,…
Deploying Vision-Language Models (VLMs) on edge devices is challenged by resource constraints and performance degradation under distribution shifts. While test-time adaptation (TTA) can counteract such shifts, existing methods are too…
Residual networks have shown great success and become indispensable in recent deep neural network models. In this work, we aim to re-investigate the training process of residual networks from a novel social psychology perspective of…
Each year, deep learning demonstrates new and improved empirical results with deeper and wider neural networks. Meanwhile, with existing theoretical frameworks, it is difficult to analyze networks deeper than two layers without resorting to…
While deeper and wider neural networks are actively pushing the performance limits of various computer vision and machine learning tasks, they often require large sets of labeled data for effective training and suffer from extremely high…
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,…
Besides the classical offline setup of machine learning, stream learning constitutes a well-established setup where data arrives over time in potentially non-stationary environments. Concept drift, the phenomenon that the underlying…
We propose a framework to continuously learn object-centric representations for visual learning and understanding. Existing object-centric representations either rely on supervisions that individualize objects in the scene, or perform…
Methods for Visual Question Anwering (VQA) are notorious for leveraging dataset biases rather than performing reasoning, hindering generalization. It has been recently shown that better reasoning patterns emerge in attention layers of a…
Predictive models that generalize well under distributional shift are often desirable and sometimes crucial to building robust and reliable machine learning applications. We focus on distributional shift that arises in causal inference from…
Understanding whether deep neural networks are effectively optimized remains challenging, as training occurs in highly nonconvex landscapes and standard metrics provide limited visibility into layer-wise learning quality. This challenge is…
The implicit bias induced by the training of neural networks has become a topic of rigorous study. In the limit of gradient flow and gradient descent with appropriate step size, it has been shown that when one trains a deep linear network…
We give the first provably efficient algorithms for learning neural networks with distribution shift. We work in the Testable Learning with Distribution Shift framework (TDS learning) of Klivans et al. (2024), where the learner receives…