Zobrazeno 1 - 10
of 2 564
pro vyhledávání: '"Reservoir sampling"'
Online learning methods, like the seminal Passive-Aggressive (PA) classifier, are still highly effective for high-dimensional streaming data, out-of-core processing, and other throughput-sensitive applications. Many such algorithms rely on fast adapt
Externí odkaz:
http://arxiv.org/abs/2410.23601
Prior-free Balanced Replay: Uncertainty-guided Reservoir Sampling for Long-Tailed Continual Learning
Even in the era of large models, one of the well-known issues in continual learning (CL) is catastrophic forgetting, which is significantly challenging when the continual data stream exhibits a long-tailed distribution, termed as Long-Tailed Continua
Externí odkaz:
http://arxiv.org/abs/2408.14976
We present MIRReS, a novel two-stage inverse rendering framework that jointly reconstructs and optimizes the explicit geometry, material, and lighting from multi-view images. Unlike previous methods that rely on implicit irradiance fields or simplifi
Externí odkaz:
http://arxiv.org/abs/2406.16360
Sampling over joins is a fundamental task in large-scale data analytics. Instead of computing the full join results, which could be massive, a uniform sample of the join results would suffice for many purposes, such as answering analytical queries or
Externí odkaz:
http://arxiv.org/abs/2404.03194
Autor:
Meligrana, Adriano
Reservoir sampling techniques can be used to extract a sample from a population of unknown size, where units are observed sequentially. Most of attention has been placed to sampling without replacement, with only a small number of studies focusing on
Externí odkaz:
http://arxiv.org/abs/2403.20256
Autor:
Szydlo, Tomasz
The growing number of IoT devices and their use to monitor the operation of machines and equipment increases interest in anomaly detection algorithms running on devices. However, the difficulty is the limitations of the available computational and me
Externí odkaz:
http://arxiv.org/abs/2206.14265
Autor:
Chen, Zhiyi, Lin, Tong
Task-free online continual learning aims to alleviate catastrophic forgetting of the learner on a non-iid data stream. Experience Replay (ER) is a SOTA continual learning method, which is broadly used as the backbone algorithm for other replay-based
Externí odkaz:
http://arxiv.org/abs/2108.09592
Continual learning from a sequential stream of data is a crucial challenge for machine learning research. Most studies have been conducted on this topic under the single-label classification setting along with an assumption of balanced label distribu
Externí odkaz:
http://arxiv.org/abs/2009.03632
We consider communication-efficient weighted and unweighted (uniform) random sampling from distributed data streams presented as a sequence of mini-batches of items. This is a natural model for distributed streaming computation, and our goal is to sh
Externí odkaz:
http://arxiv.org/abs/1910.11069
We consider message-efficient continuous random sampling from a distributed stream, where the probability of inclusion of an item in the sample is proportional to a weight associated with the item. The unweighted version, where all weights are equal,
Externí odkaz:
http://arxiv.org/abs/1904.04126