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 new method for distilling predictions from a teacher model to a student model without original training data.
We are concerned with modeling the strength of links in networks by taking into account how often those links are used. Link usage is a strong indicator of how closely two nodes are related, but existing network models in Bayesian Statistics and Machine Learning are able to predict only wether a link exists at all. As …
High throughput sequencing techniques have highly impactedon modern biology, widening the gap between sequenced andannotated data. Automatic annotation tools are thereforeof the foremost importance to guide biologists' experiments. However, most of the state-of-the-art methods rely on annotation transfer, offering reli…
Quantile TD learning outperforms classical TD learning for value estimation.
In safety-critical applications a probabilistic model is usually required to be calibrated, i.e., to capture the uncertainty of its predictions accurately. In multi-class classification, calibration of the most confident predictions only is often not sufficient. We propose and study calibration measures for multi-class…
This paper explores sequential modelling of polyphonic music with deep neural networks. While recent breakthroughs have focussed on network architecture, we demonstrate that the representation of the sequence can make an equally significant contribution to the performance of the model as measured by validation set loss…
MD-split+ creates locally valid prediction regions for complex data.
Proofs show finite subgroups of homeomorphism groups are almost nilpotent.
We are now witnessing the increasing availability of event stream data, i.e., a sequence of events with each event typically being denoted by the time it occurs and its mark information (e.g., event type). A fundamental problem is to model and predict such kind of marked temporal dynamics, i.e., when the next event wil…
By design, discriminatively trained neural network classifiers produce reliable predictions only for in-distribution samples. For their real-world deployments, detecting out-of-distribution (OOD) samples is essential. Assuming OOD to be outside the closed boundary of in-distribution, typical neural classifiers do not c…
Efficiently trains deep Gaussian processes with sparse approximations.
Paper proposes faster adaptation to distribution shifts in online settings.
Accurate time series prediction over long future horizons is challenging and of great interest to both practitioners and academics. As a well-known intelligent algorithm, the standard formulation of Support Vector Regression (SVR) could be taken for multi-step-ahead time series prediction, only relying either on iterat…
A framework to explain decoder-only sequence classification models using intermediate predictions.
BART is extended to handle various response variables.
Bayesian optimization of antibodies learns from immune system evolution.
This study tackles mutual fund portfolio prediction, focusing on novel items.
The paper aims to mathematically define and learn abstractions from data.
This work approximates full conformal prediction for neural networks without sample splitting.
The objective of this work is to study the applicability of various Machine Learning algorithms for prediction of some rock properties which geoscientists usually define due to special lab analysis. We demonstrate that these special properties can be predicted only basing on routine core analysis (RCA) data. To validat…
UCSL combines clustering with supervised learning to discover interpretable subtypes.
COMA combines prediction sets from multiple models for online, adaptive prediction.
Active learning selects most informative unlabeled samples for labeling.
This paper tackles graph translation challenges by predicting both node and edge attributes simultaneously.
We consider the problem of predicting the next observation given a sequence of past observations, and consider the extent to which accurate prediction requires complex algorithms that explicitly leverage long-range dependencies. Perhaps surprisingly, our positive results show that for a broad class of sequences, there …
This research improves financial market predictions using LSTM networks.
Meta-learning framework for few-shot one-class classification using order-equivariant networks.