Research
On-device research index

arXiv research

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.

168,742 papers · 148 categories

Trend · papers per month

9.2%18.5%27.7%37.0% · Jun 202019922001200920172026
48 results for In-Distribution Performance

The paper shows strong correlation between in-distribution and out-of-distribution performance in various machine learning models.

problem Understanding reliability of machine learning systems in unseen environments.
method Empirical analysis of various models and distribution shifts on CIFAR-10, ImageNet, and other datasets.
result Out-of-distribution performance is strongly correlated with in-distribution performance across different models and distribution shifts.

Deep ensembles outperform deep ensembles of Bayesian neural networks on in-distribution data.

problem Improving model calibration and uncertainty quantification in Bayesian Neural Networks.
method Systematic investigation of deep ensembles of Bayesian Neural Networks across various datasets and architectures.
result Deep ensembles consistently outperform deep ensembles of Bayesian neural networks on in-distribution data.

In-N-Out improves model robustness to out-of-distribution data.

problem Learning robust models with few in-distribution labeled examples.
method Pre-training with auxiliary information and self-training with pseudolabels.
result In-N-Out outperforms auxiliary inputs or outputs alone on both in-distribution and OOD error.

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…

2019-10-09abs ↗pdf ↗

Monotonic relationship found between in-distribution and out-of-distribution performance.

problem Understanding performance of machine learning models under distribution shifts.
method Analyzing ridge-regularized models and linear inverse problems under covariate shift.
result Monotonic relationship between in-distribution and out-of-distribution performance for certain models.

New method identifies distribution grid outages using smart meter data.

problem Outages in urban distribution grids due to DERs and smart meters' last gasp signals.
method Data-driven approach based on stochastic time series analysis and maximum likelihood estimation.
result Proves optimal performance in identifying distribution grid outages using smart meter data.

Distributed machine learning is an approach allowing different parties to learn a model over all data sets without disclosing their own data. In this paper, we propose a weighted distributed differential privacy (WD-DP) empirical risk minimization (ERM) method to train a model in distributed setting, considering differ…

2019-10-23abs ↗pdf ↗

Deep learning models are known to be overconfident in their predictions on out of distribution inputs. This is a challenge when a model is trained on a particular input dataset, but receives out of sample data when deployed in practice. Recently, there has been work on building classifiers that are robust to out of dis…

2018-12-01abs ↗pdf ↗

ATA optimizes task allocation in distributed machine learning.

problem Greedy task allocation leads to inefficiencies in distributed machine learning.
method Adaptive Task Allocation (ATA) adapts to unknown computation time distributions.
result ATA identifies optimal task allocation without prior knowledge of computation times.

Calibrated ensembles improve both ID and OOD accuracy in distribution shift.

problem Desired balance between in-distribution and out-of-distribution accuracy.
method Ensemble standard and robust models, calibrating on ID data only.
result ID-calibrated ensembles outperform state-of-the-art methods on multiple datasets.

New framework detects out-of-distribution data by considering intrinsic ID attributes in outliers.

problem Deploying reliable machine learning systems requires effective out-of-distribution detection.
method Structured multi-view-based out-of-distribution detection learning (MVOL) framework.
result MVOL effectively utilizes both auxiliary OOD datasets and wild datasets with noisy in-distribution data.

Discriminatively trained neural classifiers can be trusted, only when the input data comes from the training distribution (in-distribution). Therefore, detecting out-of-distribution (OOD) samples is very important to avoid classification errors. In the context of OOD detection for image classification, one of the recen…

2019-04-27abs ↗pdf ↗

New method calibrates deep models for both in-distribution and out-of-distribution samples.

problem Ensuring calibration for deep models in safety-critical applications, especially in OOD regions.
method Geodesic distance and Gaussian kernel to calibrate deep models.
result Proposed KDF and KDN methods achieve well-calibrated posteriors for both in-distribution and out-of-distribution samples.

Study shows different trajectory prediction models generalize better under OoD conditions.

problem Comparing trajectory prediction models' robustness across different datasets.
method Training models on Argoverse 2 and testing on Waymo Open Motion, and vice versa, with various augmentation strategies.
result Smallest model with highest inductive bias performs best in OoD generalization.

We study the explore-exploit tradeoff in distributed cooperative decision-making using the context of the multiarmed bandit (MAB) problem. For the distributed cooperative MAB problem, we design the cooperative UCB algorithm that comprises two interleaved distributed processes: (i) running consensus algorithms for estim…

2015-12-21abs ↗pdf ↗

Single neural networks can match deep ensembles' benefits without the complexity.

problem The effectiveness and necessity of deep ensembles in neural network models.
method Demonstrated limitations of ensemble diversity and OOD performance in deep ensembles compared to a single larger model.
result A single neural network can replicate deep ensembles' benefits in uncertainty quantification and robustness.

New methods improve anomaly detection in deep networks by leveraging hierarchical likelihoods and multi-scale features.

problem Challenges in detecting anomalies in high-level features due to model bias and domain prior.
method Two methods: 1) Log likelihood ratios between in-distribution and general distribution models, 2) Multi-scale likelihood contribution.
result Strong anomaly detection performance in unsupervised setting, slightly underperforming supervised methods.

This work analyzes how multi-agent reinforcement learning can bridge the gap to reality in distributed multi-robot systems.

problem Collaborative learning in distributed multi-robot systems with varying sensors and actuators.
method Simulation-based analysis using PPO and Bullet physics engine, considering different types of perturbations.
result PPO's robustness is affected by the presence of different types of perturbations and the number of agents experiencing them.

Analyzes generalization error in distributed linear regression.

problem Understanding generalization performance in distributed learning.
method Analytical characterization of generalization error in linear regression with distributed learning.
result Generalization error increases dramatically when nodes estimate close to the number of observations.

A new method uses matrix sketches for efficient graph clustering in dynamic environments.

problem Efficiently clustering large, dynamic graphs in distributed memory systems.
method Inspired by spectral clustering, the approach uses random dimension-reducing projections to derive matrix sketches.
result The method produces embeddings that yield performant clustering results in a fully-dynamic stochastic block model stream.

Paper studies fundamental limits of communication in distributed learning.

problem Communication efficiency in model aggregation for distributed learning.
method Rate-Distortion approach to model aggregation as a vector Gaussian CEO problem.
result Derives rate region bound and sum-rate-distortion function for model aggregation.

This work shows how exploiting gradient alignment can improve distributed and federated learning performance.

problem Misalignment of gradients across clients in distributed and federated learning.
method Utilizing implicit regularization through a novel GradAlign algorithm that induces gradient alignment with large mini-batches.
result Improvements in test accuracies and generalization performance.

New algorithm uses PSO to optimize DNN training parameters in distributed systems.

problem Reducing synchronization frequency in DNN training leads to poor convergence.
method Integrates PSO into distributed training to automatically compute new parameters.
result Proposed algorithm outperforms synchronous methods in distributed DNN training.

Hierarchical VAEs detect out-of-distribution data by identifying low-level in-distribution features.

problem Out-of-distribution data often has in-distribution low-level features, leading to misleading likelihood estimates in deep generative models.
method Developed a fast, scalable, unsupervised likelihood-ratio score for out-of-distribution detection based on hierarchical variational autoencoders.
result Achieved state-of-the-art results on out-of-distribution detection across various data and model combinations.

Paper introduces a new robust loss function for RL.

problem Heuristic selection of threshold parameters in quantile Huber loss.
method Derived from Wasserstein distance, captures noise in quantile values.
result Enhances robustness against outliers and enables parameter adjustment.

Vanilla CNNs, as uncalibrated classifiers, suffer from classifying out-of-distribution (OOD) samples nearly as confidently as in-distribution samples. To tackle this challenge, some recent works have demonstrated the gains of leveraging available OOD sets for training end-to-end calibrated CNNs. However, a critical que…

2019-10-18abs ↗pdf ↗

New RL algorithm explains why deep learning works in stochastic environments.

problem Why deep RL algorithms perform well in practice despite using random exploration.
method Introducing SQIRL, an iterative RL algorithm that separates exploration and learning.
result Effective horizon explains why deep RL works in stochastic environments.

Deep neural networks(NNs) have achieved impressive performance, often exceed human performance on many computer vision tasks. However, one of the most challenging issues that still remains is that NNs are overconfident in their predictions, which can be very harmful when this arises in safety critical applications. In …

2018-12-08abs ↗pdf ↗

This work evaluates uncertainty in deep Gaussian processes.

problem Uncertainty quantification in deep Gaussian processes.
method Hierarchical deep Gaussian processes (DGPs) and Deep Sigma Point Processes (DSPPs) evaluated on regression and classification tasks.
result DSPPs provide strong in-distribution calibration but are less robust under distribution shift compared to ensembles.

This paper analyzes user-level local differential privacy in distributed systems.

problem The relationship between user-level and item-level local differential privacy under the local model is complex.
method The paper analyzes the mean estimation problem and applies it to stochastic optimization, classification, and regression. It proposes adaptive strategies to achieve optimal performance at all privacy levels.
result The proposed methods are minimax optimal up to logarithmic factors and show that user-level DP can lead to faster convergence rates than item-level DP.

The paper bridges theory and practice in query-driven selectivity learning.

problem Insufficient theoretical understanding of query-driven selectivity learning.
method Demonstrates learnability of selectivity predictors and establishes favorable OOD generalization error bounds.
result Theoretical advances improve OOD generalization of query-driven selectivity models.

Unified framework analyzes privacy risks from gradients in distributed learning.

problem Analyzing inference privacy risks from gradients in machine learning.
method Unified game-based framework for various attacks, including attribute, property, distributional, and user disclosures.
result Demonstrates inefficacy of data aggregation for privacy against inference attacks.

Paper addresses privacy and communication in distributed learning, achieving optimal performance.

problem Balancing privacy, communication, and accuracy in distributed learning and estimation.
method Developed novel encoding and decoding mechanisms for mean and frequency estimation under local differential privacy and communication constraints.
result Achieved optimal privacy and communication efficiency in mean and frequency estimation.