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.
A method to reduce memory usage in NAS by pruning the search space.
Recent studies on automatic neural architectures search have demonstrated significant performance, competitive to or even better than hand-crafted neural architectures. However, most of the existing network architecture tend to use residual, parallel structures and concatenation block between shallow and deep features …
PARMESAN learns from memory without parameters for fast, efficient continual learning.
In this paper, we compare the performances of FAISS and FENSHSES on nearest neighbor search in Hamming space--a fundamental task with ubiquitous applications in nowadays eCommerce. Comprehensive evaluations are made in terms of indexing speed, search latency and RAM consumption. This comparison is conducted towards a b…
In neural architecture search (NAS), the space of neural network architectures is automatically explored to maximize predictive accuracy for a given task. Despite the success of recent approaches, most existing methods cannot be directly applied to large scale problems because of their prohibitive computational complex…
Deep Neural Networks(DNNs) require huge GPU memory when training on modern image/video databases. Unfortunately, the GPU memory is physically finite, which limits the image resolutions and batch sizes that could be used in training for better DNN performance. Unlike solutions that require physically upgrade GPUs, the G…
Recently, randomly mapping vectorial data to strings of discrete symbols (i.e., sketches) for fast and space-efficient similarity searches has become popular. Such random mapping is called similarity-preserving hashing and approximates a similarity metric by using the Hamming distance. Although many efficient similarit…
NEST optimizes deep learning training by placing devices efficiently across networks and memory.
Memory capacity of DAM scales exponentially with feature separation, unaffected by correlations.
A new memory system handles non-stationary environments by self-sizing and retaining memories.
Two novel search strategies reduce complexity for target localization with size-dependent noise.
POET enables large neural network training on tiny devices with reduced energy.
We present the first sublinear memory sketch that can be queried to find the nearest neighbors in a dataset. Our online sketching algorithm compresses an N element dataset to a sketch of size in time, where . This sketch can correctly report the nearest neighbors of any …
Quantum-assisted VAE improves similarity search in high-dimensional datasets.
Serenity optimizes neural network execution for edge devices by scheduling with optimal memory footprint.
Intense volatility in financial markets affect humans worldwide. Therefore, relatively accurate prediction of volatility is critical. We suggest that massive data sources resulting from human interaction with the Internet may offer a new perspective on the behavior of market participants in periods of large market move…
In the last decade, it has been shown that many hard AI tasks, especially in NLP, can be naturally modeled as extreme classification problems leading to improved precision. However, such models are prohibitively expensive to train due to the memory blow-up in the last layer. For example, a reasonable softmax layer for …
Improved deep learning model deployment on tiny MCUs with mixed-precision quantization.
A new L-BFGS method tackles large-scale optimization with fewer evaluations.
It is generally accepted that many time series of practical interest exhibit strong dependence, i.e., long memory. For such series, the sample autocorrelations decay slowly and log-log periodogram plots indicate a straight-line relationship. This necessitates a class of models for describing such behavior. A popular cl…
Memory networks are neural networks with an explicit memory component that can be both read and written to by the network. The memory is often addressed in a soft way using a softmax function, making end-to-end training with backpropagation possible. However, this is not computationally scalable for applications which …
Enhances neural architecture search efficiency and prevents performance collapse.
FactorMiner discovers financial alpha factors with low redundancy.
A growing interest has been witnessed recently from both academia and industry in building nearest neighbor search (NNS) solutions on top of full-text search engines. Compared with other NNS systems, such solutions are capable of effectively reducing main memory consumption, coherently supporting multi-model search and…
We demonstrate how machine learning is able to model experiments in quantum physics. Quantum entanglement is a cornerstone for upcoming quantum technologies such as quantum computation and quantum cryptography. Of particular interest are complex quantum states with more than two particles and a large number of entangle…
HardCoRe-NAS finds fitting neural networks adhering to hard resource constraints.
Neural architecture search (NAS) has been proposed to automatically tune deep neural networks, but existing search algorithms, e.g., NASNet, PNAS, usually suffer from expensive computational cost. Network morphism, which keeps the functionality of a neural network while changing its neural architecture, could be helpfu…
Generative diffusion models mimic biological memory networks, encoding associative dynamics in deep neural weights.
DrNAS improves neural architecture search with Dirichlet distribution and progressive learning.
We present a novel framework of knowledge distillation that is capable of learning powerful and efficient student models from ensemble teacher networks. Our approach addresses the inherent model capacity issue between teacher and student and aims to maximize benefit from teacher models during distillation by reducing t…
NPAS trains neural networks with a fixed parameter budget, improving performance and compactness.
During recent years there has been an increased interest in stochastic adaptations of limited memory quasi-Newton methods, which compared to pure gradient-based routines can improve the convergence by incorporating second order information. In this work we propose a direct least-squares approach conceptually similar to…
CICLAD efficiently mines frequent closed itemsets from data streams with minimal memory usage.
Memory-efficient algorithm reduces variance in off-policy RL.
We extend the well-known BFGS quasi-Newton method and its memory-limited variant LBFGS to the optimization of nonsmooth convex objectives. This is done in a rigorous fashion by generalizing three components of BFGS to subdifferentials: the local quadratic model, the identification of a descent direction, and the Wolfe …
SIM models user interests from long sequential behavior data, improving click-through rate prediction.
BINAS improves neural architecture search with interpretable models.
Neural architecture search (NAS) has a great impact by automatically designing effective neural network architectures. However, the prohibitive computational demand of conventional NAS algorithms (e.g. GPU hours) makes it difficult to \emph{directly} search the architectures on large-scale tasks (e.g. ImageNet).…
Memory-augmented neural networks (MANNs) are designed for question-answering tasks. It is difficult to run a MANN effectively on accelerators designed for other neural networks (NNs), in particular on mobile devices, because MANNs require recurrent data paths and various types of operations related to external memory a…
Hyperplane hashing aims at rapidly searching nearest points to a hyperplane, and has shown practical impact in scaling up active learning with SVMs. Unfortunately, the existing randomized methods need long hash codes to achieve reasonable search accuracy and thus suffer from reduced search speed and large memory overhe…
One-Shot Neural architecture search (NAS) attracts broad attention recently due to its capacity to reduce the computational hours through weight sharing. However, extensive experiments on several recent works show that there is no positive correlation between the validation accuracy with inherited weights from the supe…
Comprehending complex systems by simplifying and highlighting important dynamical patterns requires modeling and mapping higher-order network flows. However, complex systems come in many forms and demand a range of representations, including memory and multilayer networks, which in turn call for versatile community-det…
Efficient ANN search for sparse embeddings in ads targeting.
ConMeZO speeds up zeroth-order optimization for large language models.
Method generates resource-optimized ML models for different platforms.
Face recall is a basic human cognitive process performed routinely, e.g., when meeting someone and determining if we have met that person before. Assisting a subject during face recall by suggesting candidate faces can be challenging. One of the reasons is that the search space - the face space - is quite large and lac…
The Analog Ensemble (AnEn) method tries to estimate the probability distribution of the future state of the atmosphere with a set of past observations that correspond to the best analogs of a deterministic Numerical Weather Prediction (NWP). This model post-processing method has been successfully used to improve the fo…
GraphGP: Scalable Gaussian Processes with Vecchia's Approximation