A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
RLCache uses reinforcement learning to optimize cache management decisions.
Parrot learns optimal cache replacement policies using imitation learning.
This paper optimizes caching and model multiplexing for large model inference.
Adaptive caching strategy improves SVM training efficiency.
DEAP Cache learns prefetching, eviction, and admission using machine learning.
KVCOMM optimizes multi-agent LLM systems by reusing KV-caches, reducing redundant processing.
A deep learning model predicts future cache accesses with high accuracy.
Due to the drastic increase of mobile traffic, wireless caching is proposed to serve repeated requests for content download. To determine the caching scheme for decentralized caching networks, the content preference learning problem based on mobility prediction is studied. We first formulate preference prediction as a …
New algorithm improves cache management with delayed feedback and decaying costs.
In this paper, the distributed edge caching problem in fog radio access networks (F-RANs) is investigated. By considering the unknown spatio-temporal content popularity and user preference, a user request model based on hidden Markov process is proposed to characterize the fluctuant spatio-temporal traffic demands in F…
Freezing intermediate layers reduces DNN inference latency.
New MAB model for online caching costs.
We developed a caching method to speed up concept learning in complex knowledge bases.
Training large-scale image recognition models is computationally expensive. This raises the question of whether there might be simple ways to improve the test performance of an already trained model without having to re-train or fine-tune it with new data. Here, we show that, surprisingly, this is indeed possible. The …
New method speeds up diffusion models without sacrificing quality.
A new method for energy-efficient file delivery in small cell networks.
Machine learning models that take computer program source code as input typically use Natural Language Processing (NLP) techniques. However, a major challenge is that code is written using an open, rapidly changing vocabulary due to, e.g., the coinage of new variable and method names. Reasoning over such a vocabulary i…
In this paper we analyze, evaluate, and improve the performance of training generalized linear models on modern CPUs. We start with a state-of-the-art asynchronous parallel training algorithm, identify system-level performance bottlenecks, and apply optimizations that improve data parallelism, cache line locality, and …
Research optimizes C++ patterns for HFT, reducing latency and improving profitability.
In this paper, we propose several improvements on the block-coordinate Frank-Wolfe (BCFW) algorithm from Lacoste-Julien et al. (2013) recently used to optimize the structured support vector machine (SSVM) objective in the context of structured prediction, though it has wider applications. The key intuition behind our i…
Accelerates data loading in deep neural network training by 30x.
LATM framework uses LLMs to create and reuse tools for efficient problem-solving.
Hyperparameter tuning of multi-stage pipelines introduces a significant computational burden. Motivated by the observation that work can be reused across pipelines if the intermediate computations are the same, we propose a pipeline-aware approach to hyperparameter tuning. Our approach optimizes both the design and exe…
Typical large-scale recommender systems use deep learning models that are stored on a large amount of DRAM. These models often rely on embeddings, which consume most of the required memory. We present Bandana, a storage system that reduces the DRAM footprint of embeddings, by using Non-volatile Memory (NVM) as the prim…
FibQuant improves KV-cache compression for long-context inference.
We address challenges of active learning under scarce informational resources in non-stationary environments. In real-world settings, data labeled and integrated into a predictive model may become invalid over time. However, the data can become informative again with switches in context and such changes may indicate un…
Paper proposes EEIPU, a memoization-aware BO algorithm to reduce hyperparameter tuning costs.
Developing efficient and scalable algorithms for Latent Dirichlet Allocation (LDA) is of wide interest for many applications. Previous work has developed an O(1) Metropolis-Hastings sampling method for each token. However, the performance is far from being optimal due to random accesses to the parameter matrices and fr…
This paper is about metric data structures in high-dimensional or non-Euclidean space that permit cached sufficient statistics accelerations of learning algorithms. It has recently been shown that for less than about 10 dimensions, decorating kd-trees with additional "cached sufficient statistics" such as first and sec…
Low power digital signal processors (DSPs) typically have a very limited amount of memory in which to cache data. In this paper we develop efficient bottleneck feature (BNF) extractors that can be run on a DSP, and retrain a baseline large-vocabulary continuous speech recognition (LVCSR) system to use these BNFs with o…
New algorithm reduces costs and latency for large language model inference.
Generating logical form equivalents of human language is a fresh way to employ neural architectures where long short-term memory effectively captures dependencies in both encoder and decoder units. The logical form of the sequence usually preserves information from the natural language side in the form of similar token…
DaRE forests enable efficient data deletion from random forests.
This paper improves convergence guarantees for SGD algorithms in non-convex smooth functions.
We present CYCLADES, a general framework for parallelizing stochastic optimization algorithms in a shared memory setting. CYCLADES is asynchronous during shared model updates, and requires no memory locking mechanisms, similar to HOGWILD!-type algorithms. Unlike HOGWILD!, CYCLADES introduces no conflicts during the par…
Paper accelerates K-means clustering for large sparse document data.
Transformer is a popularly used neural network architecture, especially for language understanding. We introduce an extended and unified architecture that can be used for tasks involving a variety of modalities like image, text, videos, etc. We propose a spatio-temporal cache mechanism that enables learning spatial dim…
Optimizes web page freshness with limited crawling frequencies.
Efficiently combines autoregressive and set-based models for joint distributions.
IVF k-means algorithm improves performance on large sparse data sets.
Paper details Hilbert-curve for high-performance data mining.
Automated process discovery is a class of process mining methods that allow analysts to extract business process models from event logs. Traditional process discovery methods extract process models from a snapshot of an event log stored in its entirety. In some scenarios, however, events keep coming with a high arrival…
Memory-augmented neural networks consisting of a neural controller and an external memory have shown potentials in long-term sequential learning. Current RAM-like memory models maintain memory accessing every timesteps, thus they do not effectively leverage the short-term memory held in the controller. We hypothesize t…
Study uses three sources to evaluate language models fairly.
In this paper we study a family of variance reduction methods with randomized batch size---at each step, the algorithm first randomly chooses the batch size and then selects a batch of samples to conduct a variance-reduced stochastic update. We give the linear convergence rate for this framework for composite functions…
WildCat efficiently compresses neural network attention mechanisms.
Online structure learning approaches, such as those stemming from Statistical Relational Learning, enable the discovery of complex relations in noisy data streams. However, these methods assume the existence of fully-labelled training data, which is unrealistic for most real-world applications. We present a novel appro…
In this paper, we propose a dual memory structure for reinforcement learning algorithms with replay memory. The dual memory consists of a main memory that stores various data and a cache memory that manages the data and trains the reinforcement learning agent efficiently. Experimental results show that the dual memory …