AIQB
ResearchOrdinary

Gap-free Differentially Private PCA for Gaussian Data

Source: arXiv·

Summary

We give a gap-free differentially private algorithm for the principal component analysis (PCA) problem with Gaussian data.
CategoryAI Research & Papers
TierOrdinary
Published
Indexed by AIQB
SourcearXiv
AIQB record IDintel-926c8dcafcef4bcd6bece6e2
Read original source ↗View data sourceMore Research

Related stories

Matched by category, entity tags and source

ResearchOrdinary
Learning to Stop without Learning to Stop: Self-Supervised Confidence Training Improves Reasoning Efficiency
Reasoning models often generate very long reasoning traces, making inference computationally expensive. Existing approaches typically improve efficiency either through inference-time early-stopping mechanisms or by explicitly encouraging s…
Source: arXiv · GPT / Qwen
ResearchOrdinary
First-Order Stationarity of Reverse Diffusions
Recent literature has shown a strong connection between optimization and sampling. We develop the corresponding first-order theory for diffusion models. First, the SDE-based reverse-time flows of overdamped and underdamped Langevin diffusi…
Source: arXiv
ResearchOrdinary
Statistical attribute alignment for black-box generative AI via output post-processing
Generative AI systems are increasingly used, but aligning their outputs with user requirements poses a continuing challenge. Here, we aim to ensure that the distribution of an attribute of an AI-generated output aligns with a user-specifie…
Source: arXiv
ResearchOrdinary
User Model Extraction via Belief Self-Distillation
Large language models (LLMs) implicitly infer attributes of their users and adapt their behavior accordingly, yet these beliefs remain difficult to inspect and causally manipulate. We introduce Belief Self-Distillation (BSD), a unified rea…
Source: arXiv
ResearchOrdinary
New LoRA Skills Should Read but Never Write
Low-rank adapters (LoRA) make it cheap to fine-tune a large language model once per task, but combining several independently trained adapters into one model remains difficult: merging the updates in weight space causes interference, retra…
Source: arXiv
ResearchOrdinary
Common-Mode Collapse and Recovery in Direct Feedback Alignment
Direct feedback alignment (DFA) trains hidden layers through fixed random projections of output error. With tanh hidden units and independent sigmoid outputs, plain stochastic gradient descent can stall near the loss of a constant predicto…
Source: arXiv
ResearchOrdinary
Compact Documentation for Coding Agents: A Benchmark, an Optimizer, and Why It Does Not Transfer
We investigate whether natural-language documentation helps coding agents resolve software issues, and we build the tools to construct and evaluate it. We introduce a roundtrip benchmark that scores code descriptions by whether code regene…
Source: arXiv
ResearchOrdinary
Trust Guided Decision Transformer
Decision Transformer performance degrades on long rollouts because the conditioning context drifts out of the training distribution. We show that this drift is visible through the model's own next state prediction error, which rises during…
Source: arXiv
ResearchOrdinary
OC-GS: Gaussian Splatting for Irregular Turntable Capture
Uneven rotation and dropped frames make equal-angle assumptions unreliable for turntable reconstruction. We present OC-GS, an object-centric Gaussian splatting that refines each image's angle while maintaining a shared camera, rotation axi…
Source: arXiv
ResearchOrdinary
Strategically Diverse Sampling for Self-Training
Many LLM training and inference methods, including RL and test-time scaling, depend on repeated sampling, but benefit only when the responses meaningfully differ. Self-training faces the same challenge: training data is typically construct…
Source: arXiv · Qwen