Search Results for author:
Found 23 papers, 3 papers with code
NoMAD-Attention: Efficient LLM Inference on CPUs Through Multiply-add-free Attention
Large language model inference on Central Processing Units (CPU) is challenging due to the vast quantities of expensive Multiply-Add (MAD) matrix operations in the attention computations.
KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache
This memory demand increases with larger batch sizes and longer context lengths.
LLM Multi-Agent Systems: Challenges and Open Problems
This paper explores existing works of multi-agent systems and identifies challenges that remain inadequately addressed.
LETA: Learning Transferable Attribution for Generic Vision Explainer
To address this problem, we develop a pre-trained, DNN-based, generic explainer on large-scale image datasets, and leverage its transferability to explain various vision models for downstream tasks.
Zen: Near-Optimal Sparse Tensor Synchronization for Distributed DNN Training
We then systematically explore the design space of communication schemes for sparse tensors and find the optimal one.
Winner-Take-All Column Row Sampling for Memory Efficient Adaptation of Language Model
While the model parameters do contribute to memory usage, the primary memory bottleneck during training arises from storing feature maps, also known as activations, as they are crucial for gradient calculation.
Compress, Then Prompt: Improving Accuracy-Efficiency Trade-off of LLM Inference with Transferable Prompt
Thus, optimizing this accuracy-efficiency trade-off is crucial for the LLM deployment on commodity hardware.
A Theoretical Analysis Of Nearest Neighbor Search On Approximate Near Neighbor Graph
Current theoretical literature focuses on greedy search on exact near neighbor graph while practitioners use approximate near neighbor graph (ANN-Graph) to reduce the preprocessing time.
Adaptive and Dynamic Multi-Resolution Hashing for Pairwise Summations
In this paper, we propose Adam-Hash: an adaptive and dynamic multi-resolution hashing data-structure for fast pairwise summation estimation.
Dynamic Maintenance of Kernel Density Estimation Data Structure: From Practice to Theory
In this work, we focus on the dynamic maintenance of KDE data structures with robustness to adversarial queries.
Sublinear Time Algorithm for Online Weighted Bipartite Matching
Online bipartite matching is a fundamental problem in online algorithms.
Proximity Graph Maintenance for Fast Online Nearest Neighbor Search
Given a vertex deletion request, we thoroughly investigate solutions to update the connections of the vertex.
Locality Sensitive Teaching
However, as one of the most influential and practical MT paradigms, iterative machine teaching (IMT) is prohibited on IoT devices due to its inefficient and unscalable algorithms.
Raw Nav-merge Seismic Data to Subsurface Properties with MLP based Multi-Modal Information Unscrambler
This paradigm breaks the SI into local inversion tasks, which predicts each small chunk of subsurface properties using surrounding seismic data.
Breaking the Linear Iteration Cost Barrier for Some Well-known Conditional Gradient Methods Using MaxIP Data-structures
In this work, we focus on improving the per iteration cost of CGM.
PairConnect: A Compute-Efficient MLP Alternative to Attention
The dot product self-attention in Transformer allows us to model interactions between words.
Sublinear Least-Squares Value Iteration via Locality Sensitive Hashing
We present the first provable Least-Squares Value Iteration (LSVI) algorithms that have runtime complexity sublinear in the number of actions.
Beyond Convolutions: A Novel Deep Learning Approach for Raw Seismic Data Ingestion
We propose a fundamental shift to move away from convolutions and introduce SESDI: Set Embedding based SDI approach.
MONGOOSE: A Learnable LSH Framework for Efficient Neural Network Training
Recent advances by practitioners in the deep learning community have breathed new life into Locality Sensitive Hashing (LSH), using it to reduce memory and time bottlenecks in neural network (NN) training.
Climbing the WOL: Training for Cheaper Inference
Efficient inference for wide output layers (WOLs) is an essential yet challenging task in large scale machine learning.
Möbius Transformation for Fast Inner Product Search on Graph
We present a fast search on graph algorithm for Maximum Inner Product Search (MIPS).
On Efficient Retrieval of Top Similarity Vectors
Retrieval of relevant vectors produced by representation learning critically influences the efficiency in natural language processing (NLP) tasks.
Fast Binary Functional Search on Graph
As Approximate Nearest Neighbor Search (ANNS) techniques have specifications on metric distances, efficient searching by advanced measures is still an open question.
