… that our prospects of finding efficient agnostic PAC learning algorithms may be bleak, we …
trivial situations, efficient agnostic learning is in fact tractable. We give a learning method based …

… with bounded fan-in is efficiently learnable in an agnostic learning model. However, the …
that efficient agnostic learning of this class of neural network is as hard as learning polynomial-…

… we propose an efficient and robust Modality-agnostic (… efficient to high-performance models.
Our method comprises two plug-and-play modules that enable efficient multi-modal learning …

In this paper we present a polynomial time algorithm for agnostic PAC-learning with convex
polygons. This hypothesis class is interesting for applied machine learning, where …

… To this end, we propose an effective, efficient, model-agnostic, and post-processing method
to implement DGNN unlearning. Specifically, we first define the unlearning requests and …

… towards bridging the gap between MTL and meta-learning, both theoretically and empirically.
Theoretically, we show that MTL and gradientbased meta-learning (… -agnostic metalearning …

… For efficient training we have to adapt to different data. To achieve this, we need a flexible
learning rate schedule and reliable early stopping criterion. Popular SOTA schedulers like …

… Our objective is to achieve highly efficient and effective attack using an Orthogonal Match…
In empirical analysis, we compare FEAT with other state-ofthe-art domain-agnostic attack …

Advancing research in the emerging field of deep graph learning requires new tools to
support tensor computation over graphs. In this paper, we present the design principles and …

… agnostic learning is extremely computationally demanding, it is interesting that we can find
efficient algorithms for reliably agnostic learning … results in agnostic learning, one for learning …