Zobrazeno 1 - 10
of 2 076
pro vyhledávání: '"Karpukhin AT"'
Autor:
Dzhambulat, Mollaev, Kostin, Alexander, Maria, Postnova, Karpukhin, Ivan, Kireev, Ivan A, Gusev, Gleb, Savchenko, Andrey
Financial organizations collect a huge amount of data about clients that typically has a temporal (sequential) structure and is collected from various sources (modalities). Due to privacy issues, there are no large-scale open-source multimodal datase
Externí odkaz:
http://arxiv.org/abs/2409.17587
Autor:
Karpukhin, Ivan, Savchenko, Andrey
Long-horizon event forecasting is critical across various domains, including retail, finance, healthcare, and social networks. Traditional methods, such as Marked Temporal Point Processes (MTPP), often rely on autoregressive models to predict multipl
Externí odkaz:
http://arxiv.org/abs/2408.13131
Autor:
Abdullaeva, Irina, Filatov, Andrei, Orlov, Mikhail, Karpukhin, Ivan, Vasilev, Viacheslav, Dimitrov, Denis, Kuznetsov, Andrey, Kireev, Ivan, Savchenko, Andrey
Event sequences (ESs) arise in many practical domains including finance, retail, social networks, and healthcare. In the context of machine learning, event sequences can be seen as a special type of tabular data with annotated timestamps. Despite the
Externí odkaz:
http://arxiv.org/abs/2407.12833
Accurately forecasting multiple future events within a given time horizon is crucial for finance, retail, social networks, and healthcare applications. Event timing and labels are typically modeled using Marked Temporal Point Processes (MTPP), with e
Externí odkaz:
http://arxiv.org/abs/2406.14341
Autor:
Goddard, Charles, Siriwardhana, Shamane, Ehghaghi, Malikeh, Meyers, Luke, Karpukhin, Vlad, Benedict, Brian, McQuade, Mark, Solawetz, Jacob
The rapid expansion of the open-source language model landscape presents an opportunity to merge the competencies of these model checkpoints by combining their parameters. Advances in transfer learning, the process of fine-tuning pretrained models fo
Externí odkaz:
http://arxiv.org/abs/2403.13257
In 1970, Lawson solved the topological realization problem for minimal surfaces in the sphere, showing that any closed orientable surface can be minimally embedded in $\mathbb{S}^3$. The analogous problem for surfaces with boundary was posed by Frase
Externí odkaz:
http://arxiv.org/abs/2402.13121
Consider a Dirac operator on an oriented compact surface endowed with a Riemannian metric and spin structure. Provided the area and the conformal class are fixed, how small can the $k$-th positive Dirac eigenvalue be? This problem mirrors the maximiz
Externí odkaz:
http://arxiv.org/abs/2308.07875
Autor:
Zhdanov, Maksim, Karpukhin, Ivan
The concepts of overfitting and generalization are vital for evaluating machine learning models. In this work, we show that the popular Recall@K metric depends on the number of classes in the dataset, which limits its ability to estimate generalizati
Externí odkaz:
http://arxiv.org/abs/2306.13357
Deep ensembles are capable of achieving state-of-the-art results in classification and out-of-distribution (OOD) detection. However, their effectiveness is limited due to the homogeneity of learned patterns within ensembles. To overcome this issue, o
Externí odkaz:
http://arxiv.org/abs/2305.11616
Autor:
Lee, Hyunji, Kim, Jaeyoung, Chang, Hoyeon, Oh, Hanseok, Yang, Sohee, Karpukhin, Vlad, Lu, Yi, Seo, Minjoon
The generative retrieval model depends solely on the information encoded in its model parameters without external memory, its information capacity is limited and fixed. To overcome the limitation, we propose Nonparametric Decoding (Np Decoding) which
Externí odkaz:
http://arxiv.org/abs/2210.02068