82 citations · 151 across the 23 of their papers we have counts for
14 papers · 1 filter
TurboQuant: Online Vector Quantization with Near-optimal Distortion Rate
Amir Zandieh, Majid Daliri, Majid Hadian +1
Vector quantization, a problem rooted in Shannon's source coding theory, aims to quantize high-dimensional Euclidean vectors while minimizing distortion in their geometric structur…
PolarQuant: Quantizing KV Caches with Polar Transformation
Insu Han, Praneeth Kacham, Amin Karbasi +2
Large language models (LLMs) require significant memory to store Key-Value (KV) embeddings in their KV cache, especially when handling long-range contexts. Quantization of these KV…
Streaming Attention Approximation via Discrepancy Theory
Ekaterina Kochetkova, Kshiteej Sheth, Insu Han +2
Large language models (LLMs) have achieved impressive success, but their high memory requirements present challenges for long-context token generation. In this paper we study the s…
QJL: 1-Bit Quantized JL Transform for KV Cache Quantization with Zero Overhead
Amir Zandieh, Majid Daliri, Insu Han
Serving LLMs requires substantial memory due to the storage requirements of Key-Value (KV) embeddings in the KV cache, which grows with sequence length. An effective approach to co…
SubGen: Token Generation in Sublinear Time and Memory
Amir Zandieh, Insu Han, Vahab Mirrokni +1
Despite the significant success of large language models (LLMs), their extensive memory requirements pose challenges for deploying them in long-context token generation. The substa…
HyperAttention: Long-context Attention in Near-Linear Time
Insu Han, Rajesh Jayaram, Amin Karbasi +3
We present an approximate attention mechanism named HyperAttention to address the computational challenges posed by the growing complexity of long contexts used in Large Language M…
KDEformer: Accelerating Transformers via Kernel Density Estimation
Amir Zandieh, Insu Han, Majid Daliri +1
Dot-product attention mechanism plays a crucial role in modern deep architectures (e.g., Transformer) for sequence modeling, however, naïve exact computation of this model incurs q…
Fast Neural Kernel Embeddings for General Activations
Insu Han, Amir Zandieh, Jaehoon Lee +3
Infinite width limit has shed light on generalization and optimization aspects of deep learning by establishing connections between neural networks and kernel methods. Despite thei…
Random Gegenbauer Features for Scalable Kernel Methods
Insu Han, Amir Zandieh, Haim Avron
We propose efficient random features for approximating a new and rich class of kernel functions that we refer to as Generalized Zonal Kernels (GZK). Our proposed GZK family, genera…
Leverage Score Sampling for Tensor Product Matrices in Input Sparsity Time
David P. Woodruff, Amir Zandieh
We propose an input sparsity time sampling algorithm that can spectrally approximate the Gram matrix corresponding to the -fold column-wise tensor product of matrices using…
Scaling Neural Tangent Kernels via Sketching and Random Features
Amir Zandieh, Insu Han, Haim Avron +3
The Neural Tangent Kernel (NTK) characterizes the behavior of infinitely-wide neural networks trained under least squares loss by gradient descent. Recent works also report that NT…
Learning with Neural Tangent Kernels in Near Input Sparsity Time
Amir Zandieh
The Neural Tangent Kernel (NTK) characterizes the behavior of infinitely wide neural nets trained under least squares loss by gradient descent. However, despite its importance, the…
Beyond -Approximation for Submodular Maximization on Massive Data Streams
Ashkan Norouzi-Fard, Jakub Tarnawski, Slobodan Mitrović +3
Many tasks in machine learning and data mining, such as data diversification, non-parametric learning, kernel machines, clustering etc., require extracting a small but representati…
Random Fourier Features for Kernel Ridge Regression: Approximation Bounds and Statistical Guarantees
Haim Avron, Michael Kapralov, Cameron Musco +3
Random Fourier features is one of the most popular techniques for scaling up kernel methods, such as kernel ridge regression. However, despite impressive empirical results, the sta…