Zobrazeno 1 - 10
of 89
pro vyhledávání: '"Das, Abhimanyu"'
Motivated by the recent success of time-series foundation models for zero-shot forecasting, we present a methodology for $\textit{in-context fine-tuning}$ of a time-series foundation model. In particular, we design a pretrained foundation model that
Externí odkaz:
http://arxiv.org/abs/2410.24087
Mixture models arise in many regression problems, but most methods have seen limited adoption partly due to these algorithms' highly-tailored and model-specific nature. On the other hand, transformers are flexible, neural sequence models that present
Externí odkaz:
http://arxiv.org/abs/2311.08362
Motivated by recent advances in large language models for Natural Language Processing (NLP), we design a time-series foundation model for forecasting whose out-of-the-box zero-shot performance on a variety of public datasets comes close to the accura
Externí odkaz:
http://arxiv.org/abs/2310.10688
In many learning applications, data are collected from multiple sources, each providing a \emph{batch} of samples that by itself is insufficient to learn its input-output relationship. A common approach assumes that the sources fall in one of several
Externí odkaz:
http://arxiv.org/abs/2309.01973
Recent work has shown that simple linear models can outperform several Transformer based approaches in long term time-series forecasting. Motivated by this, we propose a Multi-layer Perceptron (MLP) based encoder-decoder model, Time-series Dense Enco
Externí odkaz:
http://arxiv.org/abs/2304.08424
We begin the study of list-decodable linear regression using batches. In this setting only an $\alpha \in (0,1]$ fraction of the batches are genuine. Each genuine batch contains $\ge n$ i.i.d. samples from a common unknown distribution and the remain
Externí odkaz:
http://arxiv.org/abs/2211.12743
We study the problem of learning generalized linear models under adversarial corruptions. We analyze a classical heuristic called the iterative trimmed maximum likelihood estimator which is known to be effective against label corruptions in practice.
Externí odkaz:
http://arxiv.org/abs/2206.04777
Probabilistic, hierarchically coherent forecasting is a key problem in many practical forecasting applications -- the goal is to obtain coherent probabilistic predictions for a large number of time series arranged in a pre-specified tree hierarchy. I
Externí odkaz:
http://arxiv.org/abs/2204.10414
We study the setting of optimizing with bandit feedback with additional prior knowledge provided to the learner in the form of an initial hint of the optimal action. We present a novel algorithm for stochastic linear bandits that uses this hint to im
Externí odkaz:
http://arxiv.org/abs/2203.04274
Autor:
Chanwala, Jeky, Jha, Deepak Kumar, Sherpa, Tsheten, Kumari, Khushbu, Barla, Preeti, Das, Abhimanyu, Dey, Nrisingha
Publikováno v:
In Current Plant Biology September 2024 39
