First ABAW 2020 Competition analyzes affective behavior tasks.
problem Automatic analysis of valence-arousal, basic expressions, and action units in real-world scenarios.
method Provided Aff-Wild2 database, described Challenges, evaluation metrics, and top-performing systems.
result Demonstrated the feasibility of automatic affective behavior analysis in real-world settings.
Two-stream model recognizes affect from audio and video.
problem Human affect recognition in real-world settings.
method Two-stream aural-visual analysis model with separate audio and visual processing.
result Model achieves promising results on Aff-Wild2 database.
FinCausal 2020 task detects financial document causality.
problem Detect causal relationships in financial documents.
method Binary classification and relation extraction tasks.
result 16 teams participated, 13 submitted system descriptions.
Study reveals the 2020 U.S. stock crash was endogenous, not caused by COVID.
problem Understanding the cause of the 2020 U.S. stock market crash.
method Applied log-periodic power law singularity (LPPLS) methodology to analyze four major U.S. stock market indexes.
result The 2020 U.S. stock market crash was endogenous, stemming from systemic instability, not COVID.
India's 2020-21 GDP growth forecast is projected at 1.9% due to COVID-19.
problem Impact of COVID-19 on India's 2020-21 GDP growth forecast.
method Quarterly GVA estimates using capacity utilisation assumptions and 2019-20 data.
result India's GDP growth in 2020-21 is expected to be 1.9%.
GeoLifeCLEF 2020 dataset pairs species observations with environmental data.
problem Understanding geographic species distribution.
method Presented a dataset of species observations with environmental features.
result Advances in location-based species recommendation.
Fuzzy Forests reduces feature space in high-dimensional survey data.
problem High-dimensional and highly correlated datasets in social science.
method Fuzzy Forests algorithm, a variant of Random Forests.
result Partisan polarization was the strongest factor in the 2020 presidential election.
Study reveals 2020 stock crashes were mostly endogenous, not exogenous.
problem Identifying the cause of the 2020 global stock market crash.
method Applied log-periodic power law singularity (LPPLS) methodology to analyze stock market indexes.
result The 2020 stock market crashes were mostly endogenous, driven by systemic instability.
2020 Census uses more noise to protect privacy than needed, improving data accuracy.
problem Ensuring privacy in census data while maintaining accuracy for policy decisions.
method Applied f f f -differential privacy to track and reduce noise across geographical levels. result The 2020 Census provides stronger privacy protections than its nominal guarantees suggest.
RoBERTa model detects counterfactual statements in text.
problem Detecting and extracting counterfactual statements from text.
method Used RoBERTa language representation model for both subtasks.
result RoBERTa achieved top performance in both subtasks at SemEval-2020.
Researchers discuss connections and distinctions between DRITR and Kallus' work, focusing on policy evaluation and efficiency.
problem Policy evaluation and efficiency under distributionally robust individualized treatment rules.
method Efficient policy evaluation using combined data and DRITR under varying sample sizes.
result Efficient value function estimates can deliver competitive performance under certain conditions but not always.
Bayesian SHMM models speech units from unannotated speech.
problem Discover latent speech units from unannotated data.
method Bayesian Subspace Hidden Markov Model (SHMM).
result System performs well on synthesis quality, lower bitrate.
Efficiently calculates privacy guarantees for 2020 Census data.
problem Evaluate privacy guarantees for 2020 U.S. Census data releases.
method Sieve-accelerated quadrature method to evaluate tail probabilities of high-dimensional convolutions.
result Achieves 1,824-fold speedup over prior methods while maintaining error tolerances.
Microdata improves inflation forecasts after major shocks, study finds.
problem Forecasting inflation in a non-stationary environment with microeconomic data.
method Developed a scan test to detect periods of micro forecast outperformance, combined with adaptive machine learning.
result Micro forecasts improve inflation predictions after major shocks, especially after 2020.
XPDNet wins MRI reconstruction challenge with neural network.
problem MRI reconstruction from under-sampled data.
method Inspired by MRI and computer vision best practices, XPDNet uses a neural network.
result XPDNet achieved state-of-the-art results in the 2020 fastMRI challenge.
Study analyzes market co-movements in critical mineral investments using change point detection and cross-sectional analysis.
problem Market dynamics in critical mineral investments during significant global events.
method Combines change-point detection (PELT algorithm) with cross-sectional analysis on ESG-ranked ETFs.
result Investors herded during market downturns and shifted to anti-herding after positive news and geopolitical shocks.
Study on excess mortality in Germany during 2020-21.
problem Analyzing excess mortality during the pandemic in Germany.
method Empirical study using official death counts.
result Provided conclusions for insurance businesses.
New approaches estimate recommendation metrics using sampling.
problem Understanding and resolving the use of sampling for recommendation evaluation.
method MLE and ME principles for empirical rank distribution recovery.
result Advantages of new approaches for top-k metrics estimation.
Bayesian optimization outperformed random search in machine learning hyperparameter tuning challenge.
problem Optimizing hyperparameters of machine learning models using derivative-free methods.
method Bayesian optimization vs. random search on real datasets.
result Bayesian optimization significantly outperformed random search in held-out objective functions.
Study examines oil and US stock market interactions during coronavirus crisis.
problem Understanding the impact of coronavirus on oil and stock markets.
method Wavelet analysis of daily data from February 18, 2020 to August 15, 2020.
result Oil prices lead US stock prices at 3-5-day cycles during the first and second parts of March and April 2020.
Discuss new policy learning objectives and methods.
problem Improving policy learning efficiency and robustness.
method Introducing curvature considerations and calibration data methods.
result Efficient retargeting and distributionally robust policies.
This article reviews datasets for COVID-19 detection using ML.
problem Lack of accessible datasets for COVID-19 detection research.
method Analyzed 96 papers on COVID-19 detection from January 2020 to June 2020.
result Identified and summarized datasets used in COVID-19 detection studies.
Mirror Langevin Algorithm converges with zero bias.
problem Achieving convergence with zero bias in discrete-time sampling.
method Discretization of Mirror Langevin Diffusion and mean-square analysis.
result Mirror Langevin Algorithm converges with zero bias.
D2KLab's approach predicts tweet engagement using two stages.
problem Predicting user engagement with tweets.
method Two-stage approach: feature learning and ensemble XGBoost.
result Ranked 22 in the 2020 RecSys Challenge leaderboard.
New RL algorithm for linear MDPs with nearly optimal regret.
problem Optimizing reinforcement learning for linear mixture Markov decision processes.
method Proposed a new Bernstein-type concentration inequality for self-normalized martingales and a computationally efficient algorithm UCRL-VTR+.
result UCRL-VTR+ achieves nearly minimax optimal regret of i l d e O ( d H T ) ilde O(dH\sqrt{T}) i l d e O ( d H T ) . A new L2D system produces calibrated probabilities of expert correctness without sacrificing accuracy.
problem Calibration of learning to defer systems for safety.
method One-vs-all classifiers with a consistent surrogate loss function.
result Proposes a calibrated L2D system that outperforms existing methods in accuracy and calibration.
New methods improve inference after prediction without strong model assumptions.
problem Improper inference after prediction can lead to invalid results.
method Angelopoulos et al. (2023) and Wang et al. (2020) propose corrections to inference.
result Angelopoulos et al. method controls type 1 error and provides correct coverage.
CVPR 2020 challenge evaluates continual learning in computer vision.
problem Making AI systems more adaptive and efficient.
method Evaluated different continual learning approaches on a common hardware with shared metrics.
result Reported main results, finalists, and prize winners.
The paper analyzes the implicit bias of SGD near loss manifold and provides new insights.
problem Understanding the implicit bias of SGD near loss manifolds in overparametrized models.
method Adapting ideas from Katzenberger (1991) to analyze SGD dynamics using a stochastic differential equation (SDE).
result SGD with label noise locally decreases the sharpness of loss, leading to a global analysis of implicit bias.
Study shows COVID-19 cases increase stock market volatility in Pakistan.
problem Impact of COVID-19 on stock market volatility in Pakistan.
method Used vector autoregressive (VAR) model to analyze data from February 25, 2020 to December 7, 2020.
result A shock to total daily coronavirus cases in Pakistan leads to a significant increase in stock market volatility.
This paper shows how to approximate any log-concave distribution using well-conditioned affine coupling flows.
problem Understanding the representational power of affine coupling flows for log-concave distributions.
method Leveraging connections between affine coupling architectures, Langevin dynamics, and Hénon maps to prove log-concave approximation.
result Any log-concave distribution can be approximated using well-conditioned affine-coupling flows.
Improved algorithm for partial recovery of tree-structured graphs with noisy data.
problem Learning Ising tree models with noisy observations.
method Symmetrized Geometric Averaging (SGA) algorithm with improved sample complexity.
result Significantly better sample complexity for partial tree recovery.
Study compares ARIMA, ETS, NNAR and hybrids for COVID-19 hospitalizations.
problem Forecasting the second wave of COVID-19 hospitalizations in Italy.
method ARIMA, ETS, NNAR, and hybrid models.
result Hybrid models outperform single models in capturing epidemic patterns.
Study resolves the Korean LVRP puzzle by showing HVRP exists but is masked by investor heterogeneity and improper intensity normalization.
problem Puzzling Low Volume Return Premium (LVRP) in Korea, contradicting global High Volume Return Premium (HVRP) evidence.
method Used Korean market data (2020-2024) to demonstrate HVRP exists but is masked by investor heterogeneity and improper intensity normalization. Normalized institutional buying intensity by market capitalization rather than trading value.
result Demonstrated a perfect monotonic relationship between highest-conviction institutional buying and positive cumulative abnormal returns, while lowest-intensity trades yield modest returns.
Study shows oil prices but not COVID-19 cases affect US economic policy uncertainty.
problem Effect of COVID-19 and crude oil prices on US economic policy uncertainty.
method Used ARDL model with daily data from January 21-March 13, 2020.
result Crude oil price dynamics increase US economic policy uncertainty, while COVID-19 cases have mixed effects.
Italy's daily COVID-19 cases stratified by age groups.
problem Analyzing the spread and impact of COVID-19 across different age groups.
method Stratified daily data of COVID-19 cases by age classes.
result Detailed insights into how age affects COVID-19 outcomes.
RL-Exec uses reinforcement learning to optimize BTC-USD liquidation, outperforming traditional methods.
problem Optimizing liquidation strategies on BTC-USD limit-order books with transient impact and latency.
method PPO agent trained on historical BTC-USD limit-order book replays, incorporating impact resilience and fees.
result RL-Exec significantly outperforms TWAP and a VWAP-like baseline on BTC-USD liquidation, with performance improving with longer execution horizons.
Model predicts COVID-19 growth in Senegal, highlighting health care capacity importance.
problem Impact of health care capacity on COVID-19 growth in Senegal.
method Compartmental model with logistic growth health care capacity, machine learning projection.
result Condition to avoid overwhelming health care system provided.
Machine learning models for COVID-19 detection and prognosis from chest images are flawed and unreliable.
problem Developing reliable machine learning models for COVID-19 diagnosis and prognosis from chest images.
method Systematic review of machine learning models published in 2020.
result None of the models identified are of clinical use due to methodological flaws and biases.
Counterexamples show deconfounder fails to control multi-cause confounding.
problem Deconfounding method fails to handle multi-cause confounding.
method Incorrectly inferring independence and joint independence from conditional independence.
result Two simple counterexamples demonstrate deconfounder's failure.
New algorithm learns regression models privately under growth condition.
problem Private learning of nonparametric regression models.
method Novel filtering procedure to output stable hypotheses for nonparametric function classes.
result Established first nonparametric private learnability guarantee for diverging fat shattering dimensions.
New methods use Kronecker-factored approximations for faster deep learning optimization.
problem Optimizing deep learning models with rich curvature information.
method Approximate Hessian using Kronecker products for efficient quasi-Newton methods.
result New methods outperform first-order methods and perform comparably to second-order methods.
Paper tackles counterfactual sentence detection and evaluation.
problem Detect and evaluate counterfactual sentences in natural language.
method Used a BERT base model for classification and a hybrid BERT Multi-Layer Perceptron for sequence identification. Introduced cascaded linear inputs to improve performance.
result Achieved an F1 score of 85.00% in Task 1 and 83.90% in Task 2.
New framework classifies high-dimensional shapes using ray intersections, establishing data requirements.
problem Classifying high-dimensional shapes in real-world data.
method Ray-based classification (RBC) framework using intersections of one-dimensional representations (rays) with shape boundaries.
result Established bounds on the number of rays necessary for shape classification, defined by key angular metrics.
Uniform convergence of interpolators proven for Gaussian data.
problem Interpolation learning in high-dimensional linear regression with Gaussian data.
method Generic uniform convergence guarantee in terms of Gaussian width.
result Consistency of interpolators for minimum-norm and near-minimal-norm cases.
Modeling human language learning with multi-checkpoint machine translation.
problem Improving machine translation quality for language education.
method Ensemble of multi-checkpoints from a single model, sampling n-best sequences.
result Achieved 37.57 macro F1 score, outperforming baseline.
Generative models improve commodity hedging using deep learning.
problem Improving risk management in commodity markets.
method Four state-of-the-art generative models adapted for commodity time series.
result Deep hedging of commodity options trained on generated time series shows promising results.
Recent pruning methods at initialization fall short of random pruning's accuracy.
problem Improving neural network accuracy through pruning at initialization.
method Various pruning methods (SNIP, GraSP, SynFlow, magnitude pruning) are evaluated; per-layer pruning decisions are proposed.
result Randomly shuffling or sampling initial weights preserves or improves accuracy, suggesting challenges with pruning heuristics.