Oceania
The Goldilocks of Pragmatic Understanding: Fine-Tuning Strategy Matters for Implicature Resolution by LLMs
Humans interpret language using beliefs and prior knowledge about the world. For example, we intuitively understand the response "I wore gloves" to the question "Did you leave fingerprints?" as meaning "No".
LinGCN: Structural Linearized Graph Convolutional Network for Homomorphically Encrypted Inference
The deployment of GCNs in the cloud raises privacy concerns due to potential adversarial attacks on client data. To address security concerns, Privacy-Preserving Machine Learning (PPML) using Homo-morphic Encryption (HE) secures sensitive client data.
A Heavy-Tailed Algebra for Probabilistic Programming
Theorem 2) is optimized (4) to correct the bulk approximation.
Curve Y our Enthusiasm: Concurvity Regularization in Differentiable Generalized Additive Models
Despite the current enthusiasm for GAMs, their susceptibility to concurvity - i.e., (possibly nonlinear) dependencies between the features - has hitherto been largely overlooked.
RS-Del: Edit Distance Robustness Certificates for Sequence Classifiers via Randomized Deletion
We present a case study on malware detection--a binary classification problem on byte sequences where classifier evasion is a well-established threat model.