:: Library Catalog

Cover Image

Saved in:

Bibliographic Details
Main Author:	Bu, Zhiqi
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	https://arxiv.org/abs/2511.04981
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Adaptive parameter-efficient fine-tuning via Hessian-informed subset selection
by: Xu, Shiyun, et al.
Published: (2025)

Convex Dominance in Deep Learning I: A Scaling Law of Loss and Learning Rate
by: Bu, Zhiqi, et al.
Published: (2026)

Gradient descent with generalized Newton's method
by: Bu, Zhiqi, et al.
Published: (2024)

Sharp Trade-Offs in High-Dimensional Inference via 2-Level SLOPE
by: Bu, Zhiqi, et al.
Published: (2025)

Towards hyperparameter-free optimization with differential privacy
by: Bu, Zhiqi, et al.
Published: (2025)

A Hessian-informed hyperparameter optimization for differential learning rate
by: Xu, Shiyun, et al.
Published: (2025)

DOPPLER: Differentially Private Optimizers with Low-pass Filter for Privacy Noise Reduction
by: Zhang, Xinwei, et al.
Published: (2024)

Differentially Private SGD Without Clipping Bias: An Error-Feedback Approach
by: Zhang, Xinwei, et al.
Published: (2023)

Tractable MCMC for Private Learning with Pure and Gaussian Differential Privacy
by: Lin, Yingyu, et al.
Published: (2023)

Pre-training Differentially Private Models with Limited Public Data
by: Bu, Zhiqi, et al.
Published: (2024)

To 2:4 Sparsity and Beyond: Neuron-level Activation Function to Accelerate LLM Pre-Training
by: Madhyastha, Meghana, et al.
Published: (2026)

Low-rank surrogate modeling and stochastic zero-order optimization for training of neural networks with black-box layers
by: Chertkov, Andrei, et al.
Published: (2025)

DiSK: Differentially Private Optimizer with Simplified Kalman Filter for Noise Reduction
by: Zhang, Xinwei, et al.
Published: (2024)

Lower bounds for one-layer transformers that compute parity
by: Hsu, Daniel
Published: (2026)

MAP: Low-compute Model Merging with Amortized Pareto Fronts via Quadratic Approximation
by: Li, Lu, et al.
Published: (2024)

Differentially Private Bias-Term Fine-tuning of Foundation Models
by: Bu, Zhiqi, et al.
Published: (2022)

A Long-Short Flow-Map Perspective for Drifting Models
by: Li, Zhiqi, et al.
Published: (2026)

Memorization capacity of deep ReLU neural networks characterized by width and depth
by: Yang, Xin, et al.
Published: (2026)

Unlearning as multi-task optimization: A normalized gradient difference approach with an adaptive learning rate
by: Bu, Zhiqi, et al.
Published: (2024)

Memory capacity of two layer neural networks with smooth activations
by: Madden, Liam, et al.
Published: (2023)

BLUR: A Bi-Level Optimization Approach for LLM Unlearning
by: Reisizadeh, Hadi, et al.
Published: (2025)

SVDformer: Direction-Aware Spectral Graph Embedding Learning via SVD and Transformer
by: Fang, Jiayu, et al.
Published: (2025)

Unsupervised Meta-Learning via Dynamic Head and Heterogeneous Task Construction for Few-Shot Classification
by: Guan, Yunchuan, et al.
Published: (2024)

Scaling ResNets in the Large-depth Regime
by: Marion, Pierre, et al.
Published: (2022)

Properties of the geometry of solutions and capacity of multi-layer neural networks with Rectified Linear Units activations
by: Baldassi, Carlo, et al.
Published: (2019)

M2oE: Multimodal Collaborative Expert Peptide Model
by: Guo, Zengzhu, et al.
Published: (2024)

Solution space and storage capacity of fully connected two-layer neural networks with generic activation functions
by: Nishiyama, Sota, et al.
Published: (2024)

SemEval-2025 Task 4: Unlearning sensitive content from Large Language Models
by: Ramakrishna, Anil, et al.
Published: (2025)

LUME: LLM Unlearning with Multitask Evaluations
by: Ramakrishna, Anil, et al.
Published: (2025)

Large language models can be zero-shot anomaly detectors for time series?
by: Alnegheimish, Sarah, et al.
Published: (2024)

Exact capacity of the \emph{wide} hidden layer treelike neural networks with generic activations
by: Stojnic, Mihailo
Published: (2024)

Are Heterogeneous Graph Neural Networks Truly Effective? A Causal Perspective
by: Yang, Xiao, et al.
Published: (2025)

A Generalizable Anomaly Detection Method in Dynamic Graphs
by: Yang, Xiao, et al.
Published: (2024)

Matrix factorization and prediction for high dimensional co-occurrence count data via shared parameter alternating zero inflated Gamma model
by: Kim, Taejoon, et al.
Published: (2024)

Asymptotics of feature learning in two-layer networks after one gradient-step
by: Cui, Hugo, et al.
Published: (2024)

Graph neural networks for residential location choice: connection to classical logit models
by: Cheng, Zhanhong, et al.
Published: (2025)

Why do zeroes happen? A model-based approach for demand classification
by: Svetunkov, Ivan, et al.
Published: (2025)

Test-Time Scaling Makes Overtraining Compute-Optimal
by: Roberts, Nicholas, et al.
Published: (2026)

Perturbative methods for non-parametric instrumental variable
by: Bu, Wei, et al.
Published: (2026)

Deep one-gate per layer networks with skip connections are universal classifiers
by: Rojas, Raul
Published: (2025)