output
19922026
Showing 2024 · cs.LGShow all

7 papers · 2 filters

cs.LG2024★ 1 cited

Gentle Local Robustness implies Generalization

Khoat Than, Dat Phan, Giang Vu

Robustness and generalization ability of machine learning models are of utmost importance in various application domains. There is a wide interest in efficient ways to analyze thos…

cs.LG2024★ 1 cited

Unsupervised Replay Strategies for Continual Learning with Limited Data

Anthony Bazhenov, Pahan Dewasurendra, Giri P. Krishnan +1

Artificial neural networks (ANNs) show limited performance with scarce or imbalanced training data and face challenges with continuous learning, such as forgetting previously learn…

cs.LG2024

Verification of Geometric Robustness of Neural Networks via Piecewise Linear Approximation and Lipschitz Optimisation

Ben Batten, Yang Zheng, Alessandro De Palma +2

We address the problem of verifying neural networks against geometric transformations of the input image, including rotation, scaling, shearing, and translation. The proposed metho…

cs.LG2024

A Geometry-Aware Algorithm to Learn Hierarchical Embeddings in Hyperbolic Space

Zhangyu Wang, Lantian Xu, Zhifeng Kong +3

Hyperbolic embeddings are a class of representation learning methods that offer competitive performances when data can be abstracted as a tree-like graph. However, in practice, lea…

cs.LG2024

Convergence Behavior of an Adversarial Weak Supervision Method

Steven An, Sanjoy Dasgupta

Labeling data via rules-of-thumb and minimal label supervision is central to Weak Supervision, a paradigm subsuming subareas of machine learning such as crowdsourced learning and s…

cs.LG2024★ 1 cited

Architectural Implications of Neural Network Inference for High Data-Rate, Low-Latency Scientific Applications

Olivia Weng, Alexander Redding, Nhan Tran +2

With more scientific fields relying on neural networks (NNs) to process data incoming at extreme throughputs and latencies, it is crucial to develop NNs with all their parameters s…

cs.LG2024★ 1 cited

Estimation of Energy-dissipation Lower-bounds for Neuromorphic Learning-in-memory

Zihao Chen, Faiek Ahsan, Johannes Leugering +2

Neuromorphic or neurally-inspired optimizers rely on local but parallel parameter updates to solve problems that range from quadratic programming to Ising machines. An ideal realiz…