arXiv:2608. 05127v1 Announce Type: cross Abstract: Achieving local differential privacy in distributed optimization while maintaining low communication cost remains challenging.
Record-level differential privacy exposes a structural misalignment in personalized federated learning when client-specific variation is low-dimensional while training repeatedly releases high-dimensi...
arXiv:2606. 26822v1 Announce Type: new Abstract: Federated Learning (FL) has become a foundational paradigm for privacy-preserving distributed intelligence, yet its scalability remains fundamentally constrained by communication bottlenecks, device heterogeneity, and the challenges of training under statistically non-IID data.
The paper proposes a privacy‑aligned personalized federated learning method that releases a private client context once and limits repeated adaptation to a fixed coefficient space, thereby reducing dimensionality misalignment. A factorized generator creates an adaptive optimization geometry that reshapes noisy updates, and most of the private‑training benefit is preserved by radial evolution. Variable‑length Gaussian quantization is used for coefficient updates, allowing the quantization error to act as the privacy perturbation and cutting protected uplink communication by a factor of 2.67 on CIFAR‑10 at ε=16 while maintaining comparable future‑client accuracy.
FedFit introduces a federated fine‑tuning framework for large language models that reduces communication overhead by using a disjoint shared vector‑bank parameterization to reconstruct adapter matrices from two compact global vector banks. It resolves the aggregation dilemma between Sum‑of‑Products and Product‑of‑Sums through an alternating optimization schedule that alternates between accurate single‑bank updates and joint updates corrected by a Residual Spectral Aggregation mechanism. The method also incorporates blockwise quantization with client‑side error feedback and provides theoretical convergence guarantees, achieving perplexity comparable to standard federated LoRA while delivering up to 100× higher compression ratios on Qwen2.5 models.
arXiv:2608. 18147v1 Announce Type: cross Abstract: Adaptive stochastic quantization (ASQ) is a recently introduced quantization approach that optimizes the Mean Squared Error (MSE) for a given input while preserving unbiasedness.
arXiv:2608.30384v1 Announce Type: new Abstract: By introducing RSLM (Rotated Scaled Lloyd-Max), a family of training-free vector quantization codecs compressing embeddings to 1--4 bits per dimension,...
arXiv:2609.40335v1 Announce Type: new Abstract: Differentially Private Stochastic Gradient Descent (DP-SGD) is a leading approach for privacy-preserving fine-tuning of large language models (LLMs). M...
arXiv:2609. 12067v1 Announce Type: new Abstract: Channel simulation has recently emerged as a useful component in machine learning systems where samples from a prescribed probability distribution are to be compressed.
arXiv:2606. 00289v1 Announce Type: new Abstract: Quantization is a fundamental tool used to compress datasets, neural network weights, and memory usage in a range of computational tasks.
arXiv:2602. 17284v2 Announce Type: replace Abstract: We consider the privacy amplification properties of a sampling scheme in which a user's data isused in $k$ steps chosen randomly and uniformly from a sequence (or set) of $t$ steps.
arXiv:2606. 18312v1 Announce Type: cross Abstract: Federated learning allows multiple clients to jointly train a shared model by sending gradient updates to a central server while keeping raw inputs local.
arXiv:2607. 03392v1 Announce Type: cross Abstract: The ever-increasing collection of personal data has created mounting pressure to develop technologies that protect sensitive aspects of individual identity.