Related papers: Decision-Aware Quadratic ReLU Replacement for HE-F…
We develop a corrective mechanism for neural network approximation: the total available non-linear units are divided into multiple groups and the first group approximates the function under consideration, the second group approximates the…
Ring Learning With Error (RLWE) algorithm is used in Post Quantum Cryptography (PQC) and Homomorphic Encryption (HE) algorithm. The existing classical crypto algorithms may be broken in quantum computers. The adversaries can store all…
We study the problem of symmetric positive semi-definite low-rank matrix completion (MC) with deterministic entry-dependent sampling. In particular, we consider rectified linear unit (ReLU) sampling, where only positive entries are…
In this work, we introduce EQ-Net: the first holistic framework that solves both the tasks of log-likelihood ratio (LLR) estimation and quantization using a data-driven method. We motivate our approach with theoretical insights on two…
Fully Homomorphic Encryption (FHE) allows arbitrarily complex computations on encrypted data without ever needing to decrypt it, thus enabling us to maintain data privacy on third-party systems. Unfortunately, sustaining deep computations…
Post-training quantization (PTQ) enables efficient deployment of large language models by mapping pretrained weights to low-bit formats without retraining, typically using a small calibration set to minimize a layer-wise calibration…
Activation functions influence behavior and performance of DNNs. Nonlinear activation functions, like Rectified Linear Units (ReLU), Exponential Linear Units (ELU) and Scaled Exponential Linear Units (SELU), outperform the linear…
Fully Homomorphic Encryption (FHE) represents a paradigm shift in cryptography, enabling computation directly on encrypted data and unlocking privacy-critical computation. Despite being increasingly deployed in real platforms, the…
Large language models (LLMs) are costly to deploy due to their large memory footprint and high inference cost. Weight-activation quantization can reduce these costs, but low-bit activation quantization remains difficult because activation…
Federated learning must address heterogeneity, strict communication and computation limits, and privacy while ensuring performance. We propose an operator-theoretic framework that maps the $L^2$-optimal solution into a reproducing kernel…
This work studies the problem of maximizing a higher degree real homogeneous multivariate polynomial over the unit sphere. This problem is equivalent to finding the leading eigenvalue of the associated symmetric tensor of higher order,…
Federated Learning (FL) facilitates the fine-tuning of Foundation Models (FMs) using distributed data sources, with Low-Rank Adaptation (LoRA) gaining popularity due to its low communication costs and strong performance. While recent work…
Rotary Position Embedding (RoPE) enables each attention head to capture multi-frequency information along the sequence dimension and is widely applied in foundation models. However, the nonlinearity introduced by RoPE complicates…
High-entropy alloys (HEAs) are metallic materials with solid solutions stabilized by high mixing entropy. Some exhibit excellent strength, often accompanied by additional properties such as magnetic, invar, corrosion, or cryogenic response.…
In collaborative intelligence applications, part of a deep neural network (DNN) is deployed on a lightweight device such as a mobile phone or edge device, and the remaining portion of the DNN is processed where more computing resources are…
Machine learning on encrypted data can address the concerns related to privacy and legality of sharing sensitive data with untrustworthy service providers. Fully Homomorphic Encryption (FHE) is a promising technique to enable machine…
Homomorphic Encryption (HE) is a commonly used tool for building privacy-preserving applications. However, in scenarios with many clients and high-latency networks, communication costs due to large ciphertext sizes are the bottleneck. In…
Positive linear programs (LPs) model many graph and operations research problems. One can solve for a $(1+\epsilon)$-approximation for positive LPs, for any selected $\epsilon$, in polylogarithmic depth and near-linear work via variations…
Many Partial Differential Equations (PDEs) do not have analytical solution, and can only be solved by numerical methods. In this context, Physics-Informed Neural Networks (PINN) have become important in the last decades, since it uses a…
Iteratively Re-weighted Least Squares (IRLS) is a method for solving minimization problems involving non-quadratic cost functions, perhaps non-convex and non-smooth, which however can be described as the infimum over a family of quadratic…