Search Results for author:
Found 37 papers, 9 papers with code
Fast Inference for Augmented Large Language Models
In this paper, we propose LAMPS, a novel LLM inference framework for augmented LLMs.
Don't Stop Me Now: Embedding Based Scheduling for LLMs
Using these predictions, we propose a prediction-based SRPT variant with limited preemption designed to account for memory overhead in LLM systems.
Learning-Augmented Frequency Estimation in Sliding Windows
We show how to utilize machine learning approaches to improve sliding window algorithms for approximate frequency estimation problems, under the ``algorithms with predictions'' framework.
Beyond Throughput and Compression Ratios: Towards High End-to-end Utility of Gradient Compression
Gradient aggregation has long been identified as a major bottleneck in today's large-scale distributed machine learning training systems.
Learning-Based Heavy Hitters and Flow Frequency Estimation in Streams
In this paper, we present the first learned competing-counter-based algorithm, called LSS, for identifying heavy hitters, top k, and flow frequency estimation that utilizes the well-known Space Saving algorithm.
SkipPredict: When to Invest in Predictions for Scheduling
SkipPredict prioritizes predicted short jobs over long jobs, and for the latter, SkipPredict applies a second round of more detailed "expensive predictions" to approximate Shortest Remaining Processing Time for these jobs.
Optimal and Near-Optimal Adaptive Vector Quantization
Quantization is a fundamental optimization for many machine-learning use cases, including compressing gradients, model weights and activations, and datasets.
THC: Accelerating Distributed Deep Learning Using Tensor Homomorphic Compression
To address this bottleneck and accelerate training, a widely-deployed approach is compression.
Proteus: A Self-Designing Range Filter
We introduce Proteus, a novel self-designing approximate range filter, which configures itself based on sampled data in order to optimize its false positive rate (FPR) for a given space requirement.
QUIC-FL: Quick Unbiased Compression for Federated Learning
Distributed Mean Estimation (DME), in which $n$ clients communicate vectors to a parameter server that estimates their average, is a fundamental building block in communication-efficient federated learning.
Tabula: Efficiently Computing Nonlinear Activation Functions for Secure Neural Network Inference
This enables an online phase where securely computing the result of a nonlinear function requires just a single round of communication, with communication cost equal to twice the number of bits of the input to the nonlinear function.
Tabula: Efficiently Computing Nonlinear Activation Functions for Private Neural Network Inference
Multiparty computation approaches to private neural network inference require significant communication between server and client, incur tremendous runtime penalties, and cost massive storage overheads.
EDEN: Communication-Efficient and Robust Distributed Mean Estimation for Federated Learning
Distributed Mean Estimation (DME) is a central building block in federated learning, where clients send local gradients to a parameter server for averaging and updating the model.
Gradient Disaggregation: Breaking Privacy in Federated Learning by Reconstructing the User Participant Matrix
We show that aggregated model updates in federated learning may be insecure.
DRIVE: One-bit Distributed Mean Estimation
We consider the problem where $n$ clients transmit $d$-dimensional real-valued vectors using $d(1+o(1))$ bits each, in a manner that allows the receiver to approximately reconstruct their mean.
Partitioned Learned Bloom Filters
Bloom filters are space-efficient probabilistic data structures that are used to test whether an element is a member of a set, and may return false positives.
How to send a real number using a single bit (and some shared randomness)
We consider both the biased and unbiased estimation problems and aim to minimize the cost.
Queues with Small Advice
Motivated by recent work on scheduling with predicted job sizes, we consider the performance of scheduling algorithms with minimal advice, namely a single bit.
Partitioned Learned Bloom Filter
Bloom filters are space-efficient probabilistic data structures that are used to test whether an element is a member of a set, and may return false positives.
Optimal Learning of Joint Alignments with a Faulty Oracle
The goal is to recover $n$ discrete variables $g_i \in \{0, \ldots, k-1\}$ (up to some global offset) given noisy observations of a set of their pairwise differences $\{(g_i - g_j) \bmod k\}$; specifically, with probability $\frac{1}{k}+\delta$ for some $\delta > 0$ one obtains the correct answer, and with the remaining probability one obtains a uniformly random incorrect answer.
The Supermarket Model with Known and Predicted Service Times
The supermarket model refers to a system with a large number of queues, where new customers choose d queues at random and join the one with the fewest customers.
Online Pandora's Boxes and Bandits
We consider online variations of the Pandora's box problem (Weitzman.
A Model for Learned Bloom Filters, and Optimizing by Sandwiching
Recent work has suggested enhancing Bloom filters by using a pre-filter, based on applying machine learning to determine a function that models the data set the Bloom filter is meant to represent.
A Model for Learned Bloom Filters and Optimizing by Sandwiching
Recent work has suggested enhancing Bloom filters by using a pre-filter, based on applying machine learning to determine a function that models the data set the Bloom filter is meant to represent.
A Bayesian Nonparametric View on Count-Min Sketch
The count-min sketch is a time- and memory-efficient randomized data structure that provides a point estimate of the number of times an item has appeared in a data stream.
Optimizing Learned Bloom Filters by Sandwiching
We provide a simple method for improving the performance of the recently introduced learned Bloom filters, by showing that they perform better when the learned function is sandwiched between two Bloom filters.
Data Structures and Algorithms
A Model for Learned Bloom Filters and Related Structures
Recent work has suggested enhancing Bloom filters by using a pre-filter, based on applying machine learning to model the data set the Bloom filter is meant to represent.
Data Structures and Algorithms
Predicting Positive and Negative Links with Noisy Queries: Theory & Practice
The {\em edge sign prediction problem} aims to predict whether an interaction between a pair of nodes will be positive or negative.
Simulated Annealing for JPEG Quantization
JPEG is one of the most widely used image formats, but in some ways remains surprisingly unoptimized, perhaps because some natural optimizations would go outside the standard that defines JPEG.
Quantized Random Projections and Non-Linear Estimation of Cosine Similarity
Random projections constitute a simple, yet effective technique for dimensionality reduction with applications in learning and search problems.
Models and Algorithms for Graph Watermarking
We introduce models and algorithmic foundations for graph watermarking.
Multimedia Data Structures and Algorithms
2-Bit Random Projections, NonLinear Estimators, and Approximate Near Neighbor Search
In this paper, we focus on a simple 2-bit coding scheme.
Theoretical Foundations of Equitability and the Maximal Information Coefficient
Introducing MIC_* also enables us to reason about the properties of MIC more abstractly: for instance, we show that MIC_* is continuous and that there is a sense in which it is a canonical "smoothing" of mutual information.
Coding for Random Projections and Approximate Near Neighbor Search
This technical note compares two coding (quantization) schemes for random projections in the context of sub-linear time approximate near neighbor search.
Coding for Random Projections
The method of random projections has become very popular for large-scale applications in statistical learning, information retrieval, bio-informatics and other applications.
Equitability Analysis of the Maximal Information Coefficient, with Comparisons
A measure of dependence is said to be equitable if it gives similar scores to equally noisy relationships of different types.
Invertible Bloom Lookup Tables
We present a version of the Bloom filter data structure that supports not only the insertion, deletion, and lookup of key-value pairs, but also allows a complete listing of its contents with high probability, as long the number of key-value pairs is below a designed threshold.
Data Structures and Algorithms Databases
