Cristian Challu

Cristian Challu

Auto-generated profile, based on publicly available information

Cristian Challu

Auton Lab, Carnegie Mellon University, Pittsburgh, Pennsylvania, U.S.A.

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
4 May 2022 in International Journal of Forecasting
Verified
Journal Article
Open access
KOKin G. Olivares
Kin G. Olivares
CCCristian Challu
Cristian Challu
GMGrzegorz Marcjasz
Grzegorz Marcjasz
Rafał WeronRafał Weron
Rafał Weron
ADArtur Dubrawski
Artur Dubrawski

23 July 2020 in American Political Science Review
Verified
Journal Article
Closed access
PDF file
CCCristian Challú
Cristian Challú
ESEnrique Seira
Enrique Seira
ASAlberto Simpser
Alberto Simpser
The credibility of election outcomes hinges on the accuracy of vote tallies. We provide causal evidence on the drivers and the downstream consequences of variation in the quality of vote tallies. Using data for the universe of polling stations in Mexico in five national elections, we document that over 40% of polling-station-level tallies display inconsistencies. Our evidence strongly suggests these inconsistencies are nonpartisan. Using data for more than 1.5 million poll workers, we show that lower educational attainment, higher workload, and higher complexity of the tally cause more inconsistencies. Finally, using an original survey of close to 80,000 poll workers together with detailed administrative data, we find that inconsistencies cause recounts and recounts lead to lower trust in electoral institutions. We discuss policy implications.

30 September 2022 in Bulletin of the Seismological Society of America
Verified
Journal Article
Closed access
PDF file
CCCristian Challu
Cristian Challu
CPChristian Poppeliers
Christian Poppeliers
PPPredrag Punoševac
Predrag Punoševac
ADArtur Dubrawski
Artur Dubrawski
Spectrally filtered principal component analysis (SFPCA) is a method we developed to discriminate between seismic source types. It is based on the well‐known principal component analysis but applied to seismic gradiometric data. In this article, we build on our previous efforts by testing the method on data collected in a small‐scale field experiment using two source types generated by manually striking the ground at various source–receiver distances (source type A) and orientations relative to the ground surface (source type B). Using the SFPCA method that we originally developed in Challu et al. (2021), we found that we can achieve good discrimination performance for a wide range of experimental geometries and noise conditions. In addition to testing the SFPCA method using a supervised learning approach, we present an SFPCA‐based discrimination method using an anomaly detection paradigm. Specifically, given a population of event‐specific data (e.g., source type A), we demonstrate that an event with source type B will fall outside the accepted population range of source type A. Thus, SFPCA may have value as a seismic discriminant in the form of an anomaly detector, which may be useful if a sufficient training dataset is not available.

25 February 2022 in arXiv
Verified
Preprint
Open access
PDF file
CCCristian Challu
Cristian Challu
PJPeihong Jiang
Peihong Jiang
YWYing Nian Wu
Ying Nian Wu
LCLaurent Callot
Laurent Callot
Multivariate time series anomaly detection has become an active area of research in recent years, with Deep Learning models outperforming previous approaches on benchmark datasets. Among reconstruction-based models, most previous work has focused on Variational Autoencoders and Generative Adversarial Networks. This work presents DGHL, a new family of generative models for time series anomaly detection, trained by maximizing the observed likelihood by posterior sampling and alternating back-propagation. A top-down Convolution Network maps a novel hierarchical latent space to time series windows, exploiting temporal dynamics to encode information efficiently. Despite relying on posterior sampling, it is computationally more efficient than current approaches, with up to 10x shorter training times than RNN based models. Our method outperformed current state-of-the-art models on four popular benchmark datasets. Finally, DGHL is robust to variable features between entities and accurate even with large proportions of missing values, settings with increasing relevance with the advent of IoT. We demonstrate the superior robustness of DGHL with novel occlusion experiments in this literature. Our code is available at https://github.com/cchallu/dghl.

8 June 2021 in arXiv
Verified
Preprint
Open access
PDF file
CCCristian Challu
Cristian Challu
KOKin G. Olivares
Kin G. Olivares
GWGus Welter
Gus Welter
ADArtur Dubrawski
Artur Dubrawski
Neural forecasting has shown significant improvements in the accuracy of large-scale systems, yet predicting extremely long horizons remains a challenging task. Two common problems are the volatility of the predictions and their computational complexity; we addressed them by incorporating smoothness regularization and mixed data sampling techniques to a well-performing multi-layer perceptron based architecture (NBEATS). We validate our proposed method, DMIDAS, on high-frequency healthcare and electricity price data with long forecasting horizons (~1000 timestamps) where we improve the prediction accuracy by 5% over state-of-the-art models, reducing the number of parameters of NBEATS by nearly 70%.

25 October 2022 in arXiv
Verified
Preprint
Open access
PDF file
CCCristian Challu
Cristian Challu
PJPeihong Jiang
Peihong Jiang
YWYing Nian Wu
Ying Nian Wu
LCLaurent Callot
Laurent Callot
In this work, we tackle two widespread challenges in real applications for time-series forecasting that have been largely understudied: distribution shifts and missing data. We propose SpectraNet, a novel multivariate time-series forecasting model that dynamically infers a latent space spectral decomposition to capture current temporal dynamics and correlations on the recent observed history. A Convolution Neural Network maps the learned representation by sequentially mixing its components and refining the output. Our proposed approach can simultaneously produce forecasts and interpolate past observations and can, therefore, greatly simplify production systems by unifying imputation and forecasting tasks into a single model. SpectraNet achieves SoTA performance simultaneously on both tasks on five benchmark datasets, compared to forecasting and imputation models, with up to 92% fewer parameters and comparable training times. On settings with up to 80% missing data, SpectraNet has average performance improvements of almost 50% over the second-best alternative. Our code is available at https://github.com/cchallu/spectranet.