Zhao Song
~Zhao_Song3
52
论文总数
26.0
年均投稿
平均评分
接收情况26/52
会议分布
ICLR
34
NeurIPS
11
ICML
7
发表论文 (52 篇)
202536 篇
4
Differential Privacy for Euclidean Jordan Algebra with Applications to Private Symmetric Cone Programming
NeurIPS 2025Poster
3
Revisiting Quantum Algorithms for Linear Regressions: Quadratic Speedups without Data-Dependent Parameters
ICLR 2025Rejected
4
Towards Sampling Data Structures for Tensor Products
ICLR 2025Rejected
4
Efficient Alternating Minimization with Applications to Weighted Low Rank Approximation
ICLR 2025Poster
4
Unlocking the Theory Behind Scaling 1-Bit Neural Networks
ICLR 2025withdrawn
4
Faster Algorithms for Structured Linear and Kernel Support Vector Machines
ICLR 2025Poster
5
Fast RoPE Attention: Combining the Polynomial Method and Fast Fourier Transform
ICLR 2025Rejected
3
Binary Hypothesis Testing for Softmax Models and Leverage Score Models
ICML 2025Poster
3
Deterministic Sparse Fourier Transform for Continuous Signals with Frequency Gap
ICML 2025Poster
4
An $O(k\log n)$ Time Fourier Set Query Algorithm
ICLR 2025Rejected
4
A Dynamic Low-Rank Fast Gaussian Transform
ICLR 2025Rejected
4
Training Overparametrized Neural Networks in Sublinear Time
ICLR 2025Rejected
4
Discrepancy Minimization in Input-Sparsity Time
ICML 2025Spotlight
4
Binary Hypothesis Testing for Softmax Models and Leverage Score Models
ICLR 2025Rejected
4
Dynamic Kernel Sparsifiers
ICLR 2025Rejected
4
Faster Algorithms for Structured John Ellipsoid Computation
NeurIPS 2025Poster
4
Attention Mechanism, Max-Affine Partition, and Universal Approximation
NeurIPS 2025Poster
4
Towards Infinite-Long Prefix in Transformer
ICLR 2025Rejected
3
One Pass Streaming Algorithm for Super Long Token Attention Approximation in Sublinear Space
ICLR 2025Rejected
4
Tensor Attention Training: Provably Efficient Learning of Higher-order Transformers
ICLR 2025Rejected
4
Efficient $k$-Sparse Band–Limited Interpolation with Improved Approximation Ratio
NeurIPS 2025Poster
4
Differential Privacy of Cross-Attention with Provable Guarantee
ICLR 2025Rejected
4
On Differentially Private String Distances
ICLR 2025withdrawn
3
Fine-grained Attention I/O Complexity: Comprehensive Analysis for Backward Passes
ICLR 2025Rejected
4
On Differential Privacy for Adaptively Solving Search Problems via Sketching
ICML 2025Oral
4
Pretrained Transformers are Deep Optimizers: Provable In-Context Learning for Deep Model Training
ICLR 2025Rejected
4
In-Context Deep Learning via Transformer Models
ICML 2025Poster
4
Computational Limits of Low-Rank Adaptation (LoRA) Fine-Tuning for Transformer Models
ICLR 2025Poster
3
Conv-Basis: A New Paradigm for Efficient Attention Inference and Gradient Computation in Transformers
ICLR 2025Rejected
4
Multi-Layer Transformers Gradient Can be Approximated in Almost Linear Time
ICLR 2025Rejected
4
Beyond Linear Approximations: A Novel Pruning Approach for Attention Matrix
ICLR 2025Poster
4
HSR-Enhanced Sparse Attention Acceleration
ICLR 2025withdrawn
4
Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency
ICLR 2025Poster
3
Fundamental Limits of Visual Autoregressive Transformers: Universal Approximation Abilities
ICML 2025Poster
3
Dissecting Submission Limit in Desk-Rejections: A Mathematical Analysis of Fairness in AI Conference Policies
ICML 2025Poster
5
High-Order Flow Matching: Unified Framework and Sharp Statistical Rates
NeurIPS 2025Poster
202416 篇
4
On Socially Fair Regression and Low-Rank Approximation
ICLR 2024Rejected
4
On Socially Fair Low-Rank Approximation and Column Subset Selection
NeurIPS 2024Poster
4
The Fine-Grained Complexity of Gradient Computation for Training Large Language Models
NeurIPS 2024Poster
4
Unmasking Transformers: A Theoretical Approach to Data Recovery via Attention Weights
ICLR 2024withdrawn
3
The Closeness of In-Context Learning and Weight Shifting for Softmax Regression
NeurIPS 2024Poster
3
Fine-tune Language Models to Approximate Unbiased In-context Learning
ICLR 2024Rejected
3
The Closeness of In-Context Learning and Weight Shifting for Softmax Regression
ICLR 2024Rejected
3
How to Capture Higher-order Correlations? Generalizing Matrix Softmax Attention to Kronecker Computation
ICLR 2024Spotlight
4
Algorithm and Hardness for Dynamic Attention Maintenance in Large Language Models
ICLR 2024Rejected
3
Low Rank Matrix Completion via Robust Alternating Minimization in Nearly Linear Time
ICLR 2024Poster
4
A Sublinear Adversarial Training Algorithm
ICLR 2024Poster
3
Parameter-Efficient Fine-Tuning via Partially Decomposable Loss Analysis and Sharing
ICLR 2024withdrawn
-
On the Similarity between Attention and SVM on the Token Separation and Selection Behavior
ICLR 2024withdrawn
3
Log-concave Sampling from a Convex Body with a Barrier: a Robust and Unified Dikin Walk
NeurIPS 2024Poster
4
On Statistical Rates and Provably Efficient Criteria of Latent Diffusion Transformers (DiTs)
NeurIPS 2024Poster
3
Metric Transforms and Low Rank Representations of Kernels for Fast Attention
NeurIPS 2024Spotlight