A new model for data with zeros or missing values.
problem Data with excess zeros or missing values.
method Composite loss framework for low-rank modeling, combining generalized low-rank and hurdle methods.
result Demonstrated on a manufacturing data set and applied to missing value imputation.
Raising statistical hurdles may not be justified due to data bias.
problem Data bias leads to unobserved results that weaken identification of revised hurdles.
method Theoretical and empirical analysis of statistical hurdles and data bias.
result Statistics targeting only published findings can be strongly identified.
Advantage amplification helps RL in slow-evolving latent-state environments.
problem Challenges in reinforcement learning for long-horizon latent-state environments.
method Temporal abstraction and aggregation methods to overcome belief state error and small action advantage.
result Proven advantage amplification in settings with slowly evolving latent states.
ImJoy simplifies deep learning for biomedical research.
problem Computational barriers limit deep learning adoption in biomedical research.
method Open-source browser-based platform for deep learning.
result Facilitates widespread reuse of deep learning solutions.
Graphs help identify unobserved confounders in causal inference.
problem Unobserved confounders skew causal inference from observational data.
method Causal graphical view and probabilistic factor models.
result The deconfounder algorithm makes valid inferences of intervention distributions.
Paper assesses synthetic data quality for machine learning competitions.
problem Ensuring synthetic data maintains the performance of real data for machine learning.
method Compares synthetic data performance to real data performance for machine learning algorithms.
result Synthetic data must preserve relative performance for machine learning applications.
Tensor analysis tackles complex multidimensional data across fields.
problem Efficiently extracting information from high-dimensional data.
method Interdisciplinary approach combining statistics, optimization, and numerical linear algebra.
result Significant progress in tensor analysis over the last decade.
Paper introduces a method to process medical images efficiently.
problem High computational cost in processing large medical image data.
method Framelet-pooling aided deep learning method to reduce complexity.
result Significant reduction in computational costs with comparable performance.
New framework bridges climate science and ML for easier climate model emulation.
problem High computational costs and mistrust of ML methods in climate models.
method Integrating climate science and machine learning perspectives to design easy-to-adopt emulators.
result Demonstrated reliability of emulators designed to address specific tasks.
Physics-inspired methods optimize SVD compression of LLMs.
problem Efficiently compressing large language models (LLMs) using SVD.
method FermiGrad for globally optimal rank selection and PivGa for lossless compression.
result Global optimization of SVD ranks and lossless compression of low-rank factors.
New proofs for curvature problems using a viscosity approach.
problem Constant rank theorems for curvature problems in compact and non-compact settings.
method Viscosity approach to prove constant rank theorems for curvature problems.
result Generalization of a differential inequality for subtrace.
We explore training an automatic modality tagger. Modality is the attitude that a speaker might have toward an event or state. One of the main hurdles for training a linguistic tagger is gathering training data. This is particularly problematic for training a tagger for modality because modality triggers are sparse for…
Simulation studies show resampling methods can be reliable for causal graph confidence.
problem Determining when causal discovery results can be trusted in real-world settings.
method Evaluation of subsampling and sampling with replacement methods.
result Subsampling and sampling with replacement performed well in indicating graph feature confidence.
Proposes methods for learning optimal dynamic treatment regimes robust to unconfoundedness violations.
problem Estimating optimal dynamic treatment regimes using historical observational data when unconfoundedness is violated.
method Utilizes proximal causal inference framework to propose three nonparametric identification methods, a (K+1)-robust method, and establish a semiparametric efficiency bound.
result Establishes the (K+1)-robust method for learning optimal dynamic treatment regimes, validating its efficiency and multiple robustness through numerical experiments.
We study the problem of robust time series analysis under the standard auto-regressive (AR) time series model in the presence of arbitrary outliers. We devise an efficient hard thresholding based algorithm which can obtain a consistent estimate of the optimal AR model despite a large fraction of the time series points …
This work simplifies Bayesian inference for neural networks by identifying influential parameter directions.
problem High computational complexity in Bayesian inference for neural networks due to high-dimensional parameter space.
method Constructing an active subspace of influential parameter directions to reduce dimensionality.
result Effective and scalable Bayesian inference achieved via reduced active subspace.
We study a robust optimal stopping problem with respect to a set $\cP$ of mutually singular probabilities. This can be interpreted as a zero-sum controller-stopper game in which the stopper is trying to maximize its pay-off while an adverse player wants to minimize this payoff by choosing an evaluation criteria from $\…
New bounds on learning from multiple distributions for VC classes.
problem Understanding the sample complexity of learning from multiple data distributions.
method Analyzing the gap between known upper and lower bounds for PAC-learnable classes.
result Recent progress on sample complexity for VC dimension d classes on k distributions.
Bayesian inference for deep neural networks using trace-class priors and MLMC.
problem Efficient Bayesian inference for deep neural networks.
method Trace-class neural network priors and Multilevel Monte Carlo method.
result Optimal computational complexity for Bayesian inference of TNN models.
Class imbalance presents a major hurdle in the application of data mining methods. A common practice to deal with it is to create ensembles of classifiers that learn from resampled balanced data. For example, bagged decision trees combined with random undersampling (RUS) or the synthetic minority oversampling technique…
Bayesian Pseudo Label Selection reduces overfitting in semi-supervised learning.
problem Overfitting in pseudo-label selection for semi-supervised learning.
method BPLS, a Bayesian framework that approximates the posterior predictive of pseudo-samples.
result BPLS outperforms traditional PLS methods, especially in high-dimensional data.
Paper proposes a new method for accurate data labeling using pairwise co-occurrences.
problem Accurate data labeling via crowdsourcing with limited data.
method Pairwise co-occurrences framework and algebraic/identifiability-enhanced algorithms.
result The approach can identify the Dawid-Skene model under realistic conditions.
A new XVA strategy rooted in balance sheet perspective improves equity process for bank shareholders.
problem Counterparty risk valuation adjustments (XVAs) in financial derivatives.
method Develops a cost-of-capital XVA strategy in a balance sheet perspective, solving explicitly in static setup and dynamically in trade context.
result Ensures a submartingale equity process corresponding to a target hurdle rate on capital at risk.
New methods handle both data and network heterogeneity in federated learning.
problem Challenges in federated learning due to data and network heterogeneity.
method Two novel client selection schemes that minimize theoretical runtime to convergence.
result Our methods are at least competitive to and up to 20 times better than existing baselines.
A significant hurdle for analyzing large sample data is the lack of effective statistical computing and inference methods. An emerging powerful approach for analyzing large sample data is subsampling, by which one takes a random subsample from the original full sample and uses it as a surrogate for subsequent computati…
ED-Filter improves eating disorder classification on Twitter.
problem High dimensionality and extensive feature sets in Twitter data for ED classification.
method Informed branch and bound search technique with hybrid greedy-based deep learning.
result Significant improvements in classification accuracy and efficiency.
This paper evaluates CFL algorithms for handling data heterogeneity in federated learning.
problem Handling data heterogeneity among clients in federated learning.
method Comparative evaluation of two state-of-the-art CFL algorithms with a proposed taxonomy of data heterogeneities.
result Analysis of CFL performance across different heterogeneity scenarios using extrinsic clustering metrics.
A deep learning framework separates overlapping nuclei in histology images.
problem Challenges in nuclear segmentation due to overlapping nuclei.
method Proposal-free spatially-aware deep learning framework with multi-scale spatial information.
result State-of-the-art performance in nuclear segmentation on a multi-organ data set.
Power-law portfolios improve diversification by scaling weights sub-linearly.
problem Optimization methods struggle with unstable pair correlations and non-Gaussian risk measures.
method Construct portfolios with penalty proportional to arbitrary order moment of returns, leading to sub-linear weight scaling.
result Infinite order power-law portfolios are perfectly diversified, improving diversification over Kelly portfolios.
Wi-Fringe recognizes named gestures using WiFi CSI without training data.
problem Lack of training data for WiFi-based gesture recognition.
method WiFi CSI values paired with activity names for recognition.
result Wi-Fringe detects activities with or without training data.
FastMuyGPs speeds up GP predictions for large datasets.
problem High cost of Gaussian process predictions for large data.
method Combines cross-validation, batching, nearest neighbors sparsification, and precomputation.
result Superior accuracy and competitive runtime compared to other methods.
Method analyzes large-scale network data to detect communication pattern shifts.
problem Analyzing large-scale time-series network data is challenging.
method Temporal encoder embedding method using ground-truth or estimated vertex labels.
result Detects communication pattern shifts across all levels of network structure.
Humorous article on pitfalls in machine learning research
problem Difficulty in reproducing and validating machine learning results
method Discussion of common issues in machine learning papers
result Highlighting watch out points for researchers
Alternative app data improves credit scoring for underserved borrowers.
problem Improving credit scoring for low-wealth and young individuals.
method Use of alternative data from app-based marketplaces, validated with TreeSHAP method.
result Alternative data sources predict financial behavior better than traditional bureau data.
Paper harmonizes medical data using flow-based causal inference.
problem Heterogeneity in medical data from different sites and protocols.
method Flow-based normalizing method for counterfactual inference on structural causal models.
result Better cross-domain generalization compared to state-of-the-art algorithms.
Paper proposes CAPE for better privacy in distributed machine learning.
problem Privacy concerns in collaborative machine learning with small datasets.
method Differential privacy with Correlation Assisted Private Estimation (CAPE).
result CAPE achieves similar performance to centralized algorithms in decentralized settings.
New algorithm for quickly deciding on tech innovations to maximize ROI.
problem Maximizing ROI in repeated decision-making for tech innovations.
method Developed a novel algorithm for learning optimal decision-making policies over innovation proposals.
result Algorithm converges to optimal policy with a rate of order min{1/(NΔ2),N−1/3}. Stable random variables are motivated by the central limit theorem for densities with (potentially) unbounded variance and can be thought of as natural generalizations of the Gaussian distribution to skewed and heavy-tailed phenomenon. In this paper, we introduce stable graphical (SG) models, a class of multivariate st…
Survive method improves model-based RL by avoiding terminal states, reducing sample complexity.
problem High sample complexity in model-free RL methods limits real-world applications.
method Introduces 'survival' concept to model-based RL, focusing on avoiding terminal states instead of maximizing rewards.
result Survive method reduces training effort by focusing on terminal states, improving model-based RL performance.
Study extends learnability equivalence to multi-class and regression, overcoming binary classification limits.
problem Equivalence of online and private learnability in multi-class and regression settings.
method Introduced a novel Littlestone dimension variant and threshold functions for multi-class classification.
result Online learnability implies private learnability in multi-class classification but not in regression.
A major hurdle to clinical translation of brain-machine interfaces (BMIs) is that current decoders, which are trained from a small quantity of recent data, become ineffective when neural recording conditions subsequently change. We tested whether a decoder could be made more robust to future neural variability by train…
Dynamic neural network toolkits such as PyTorch, DyNet, and Chainer offer more flexibility for implementing models that cope with data of varying dimensions and structure, relative to toolkits that operate on statically declared computations (e.g., TensorFlow, CNTK, and Theano). However, existing toolkits - both static…
StatFEM uses low-rank approximations to scale Bayesian statFEM for high-dimensional problems.
problem Model misspecification and scalability in high-dimensional physical systems.
method Low-rank approximation of covariance matrix, Bayesian filtering, sparse data reconstruction.
result Reconstructs sparsely observed data-generating processes with minimal loss of information.
The paper forecasts corporate distress using a novel MIDAS logistic regression method.
problem Forecasting corporate distress with right-censored data, high-dimensional predictors, and mixed-frequency data.
method The paper introduces a novel high-dimensional censored MIDAS logistic regression method that handles censoring through inverse probability weighting and employs a sparse-group penalty for mixed-frequency predictors.
result The method achieves accurate estimation and superior performance in predicting financial distress of Chinese-listed firms.
Enhances topology optimization with multiclass microstructures using latent variable Gaussian process.
problem Lack of an inherent ordering or distance measure between different classes of microstructures.
method Extended latent-variable Gaussian process (LVGP) models to multi-response LVGP (MR-LVGP) models for metamaterials.
result Improved performance through consistent load-transfer paths for micro- and macro-structures.
Retargeting improves policy learning from observational data.
problem Lack of overlap in data for different actions leads to poor policy performance.
method Optimal retargeting to induce little to no bias at the population level.
result Retargeting significantly improves policy learning procedures applied to observational data.
This paper analyzes HTL using stability theory for binary classification.
problem Analyzing HTL's theoretical behavior in binary classification tasks.
method Stability analysis of regularized empirical risk minimizers.
result Derives generalization bounds for training error, excess risk, and cross-validation.
Paper tackles catastrophic forgetting with task-based hard attention.
problem Catastrophic forgetting in neural networks after learning new tasks.
method Task-based hard attention mechanism learned through SGD.
result Reduces catastrophic forgetting by 45-80%.