SQWA improves low-precision DNNs with model averaging and quantization.
problem Designing good generalization DNNs with quantized weights.
method Floating-point model training, direct quantization, multiple low-precision models, weight averaging, re-quantization, fine-tuning, loss visualization.
result State-of-the-art results for 2-bit QDNNs on CIFAR-100 and ImageNet datasets.
Low precision operations can provide scalability, memory savings, portability, and energy efficiency. This paper proposes SWALP, an approach to low precision training that averages low-precision SGD iterates with a modified learning rate schedule. SWALP is easy to implement and can match the performance of full-precisi…
Introduces robust and decomposable AP for image retrieval.
problem Challenges in training deep neural networks with AP.
method Differentiable rank approximation and loss function design.
result ROADMAP outperforms AP approximation methods and deep models.
The paper examines the consistency of item embeddings in recommendation systems.
problem The relevance of averaging item embeddings for user or concept representation.
method Proposes an expected precision score to measure consistency and analyzes it theoretically and empirically.
result Real-world averages are less consistent for recommendation compared to theoretical assumptions.
New bounds for average graph distance using curvature and centrality.
problem Finding bounds for average graph distance.
method Using weighted average Ollivier curvature with edge betweenness centrality.
result Equality in bounds achieved for specific reflective graphs.
Group averaging boosts model accuracy without training cost.
problem Challenging training of equivariant models in physics.
method Group averaging at test time, improving accuracy.
result Improves model accuracy by up to 37% in continuous dynamics.
This paper compares average-K and top-K classification methods under ambiguity.
problem Choosing a single label in ambiguous cases leads to low precision.
method Formally characterizes ambiguity profiles and compares average-K and top-K classification methods.
result Average-K can achieve lower error rates than top-K in some ambiguous cases.
The study calculates the average genus of rational knots and links.
problem Finding the average genus of rational knots and links.
method Enumerating and calculating the number of rational knots and links with a given crossing number.
result A precise formula for the average minimal genus of rational knots and links.
Estimates scalar curvature on moduli space as genus grows.
problem Estimating scalar curvature on moduli space.
method Analyzing Weil-Petersson metric for large genus.
result Precise estimate of average scalar curvature up to 1/g2. With ever-increasing computational demand for deep learning, it is critical to investigate the implications of the numeric representation and precision of DNN model weights and activations on computational efficiency. In this work, we explore unconventional narrow-precision floating-point representations as it relates …
A new method identifies causal direction using dense functional classes.
problem Determining causal direction between two univariate, continuous-valued variables.
method Minimum Description Length (MDL) principle applied to cubic regression splines.
result LCUBE method achieves superior precision in identifying causal direction.
The paper analyzes MACD using operator theory.
problem Understanding the mathematical foundation of MACD.
method Developed a functional-analytic framework interpreting MACD as a phase-corrected, smoothed derivative operator.
result MACD is structurally equivalent to a band-pass filter and can be expressed as a finite difference of delayed and doubly averaged signals.
Today, despite decades of developments in medicine and the growing interest in precision healthcare, vast majority of diagnoses happen once patients begin to show noticeable signs of illness. Early indication and detection of diseases, however, can provide patients and carers with the chance of early intervention, bett…
New geometric metrics improve Bayesian optimization performance evaluation.
problem Current metrics lack geometric insights and cannot compare algorithms effectively.
method Proposed four geometric metrics: precision, recall, average degree, and average distance.
result Proposed metrics provide more detailed evaluation of Bayesian optimization.
Paper proves non-zero generalization boost for equivariant models.
problem Improving generalization in machine learning models.
method Analyzes simplest case of linear models, focusing on invariant/equivariant properties.
result First provably non-zero improvement in generalization for invariant/equivariant models.
Efficiently selects nearest neighbors for labeling to speed up active learning.
problem Intractable active learning and search for large-scale unlabeled data.
method Restricts candidate pool to nearest neighbors of labeled set.
result Achieved similar performance to global approach but reduced computational cost by up to 3 orders of magnitude.
The definition of the covariant space-time averaging scheme for the objects (tensors, geometric objects, etc.) on differentiable metric manifolds with a volume n-form, which has been proposed for the formulation of macroscopic gravity, is analyzed. An overview of the space-time averaging procedure in Minkowski spacetim…
BOSH optimizes functions with stochastic evaluations more efficiently and precisely.
problem Optimizing functions with noisy evaluations can lead to suboptimal solutions.
method BOSH uses a hierarchical Gaussian process to generate a growing pool of realizations.
result BOSH provides more efficient and higher-precision optimization than standard BO.
EMPIR combines low and full precision DNNs to enhance robustness against adversarial attacks.
problem Vulnerability of DNNs to adversarial attacks that misclassify inputs with small perturbations.
method Ensemble of quantized DNN models with different numerical precisions.
result EMPIR ensembles increase adversarial robustness by 42.6% on average across different tasks.
BayesBlend blends multiple models' predictions for better insurance loss predictions.
problem Improving insurance loss predictions by combining multiple models.
method Pseudo-Bayesian model averaging, stacking, and hierarchical stacking.
result BayesBlend provides a user-friendly way to blend model predictions and estimate weights.
Transformations of macroeconomic data affect machine learning forecasts, especially with regularization and nonlinearity.
problem The impact of data transformations on machine learning forecasts in macroeconomic contexts.
method Review and propose new data transformations, empirically evaluate their effects, and compare traditional and moving average rotations.
result Traditional factors should almost always be included as predictors, and moving average rotations can provide important gains.
Gradient descent stagnates in low-precision, but unbiased rounding schemes improve convergence.
problem Stagnation of gradient descent in low-precision computation.
method Proposed unbiased stochastic rounding schemes that trade zero bias for larger probability of preserving small gradients.
result Unbiased rounding methods typically improve convergence rate of gradient descent for convex problems.
Transforms game optimization dynamics into frequency domain for precise hyperparameter analysis.
problem Analyzing convergence of hyperparameters in game optimization.
method Frequency-domain framework using High-Resolution Differential Equations (HRDEs) and Laplace transforms.
result Derives precise convergence criteria for the Lookahead algorithm.
Boosts A/B test precision using auxiliary data from historical users.
problem Small sample sizes and imprecise estimates in A/B tests.
method Coupling design-based causal estimation with machine-learning models of historical user data.
result Effect estimates using auxiliary data are roughly equivalent to increasing sample size by 20%, or up to 50-80% in some cases.
New insights on Shapley value precision for tabular data predictions.
problem Precision of Shapley value explanations for individual observations.
method Conditional Shapley value estimation methods for tabular data.
result Shapley value explanations are less precise for outer observations.
Regulating causal effects through averaged constraints fails to enforce conditional independence.
problem Enforcing conditional independence in regulatory and analytic settings.
method Formulated causal masking as a linear program and analyzed the resulting enforcement problem from both regulator and optimizer perspectives.
result Averaged-constraint optimization often violates stratum-wise requirements while satisfying the averaged one exactly, and detection requires conditional-independence tests.
This paper proposes CodeX, an end-to-end framework that facilitates encoding, bitwidth customization, fine-tuning, and implementation of neural networks on FPGA platforms. CodeX incorporates nonlinear encoding to the computation flow of neural networks to save memory. The encoded features demand significantly lower sto…
New techniques improve distributed training with compressed gradients.
problem Gradient mismatch problem in local error feedback.
method Step-ahead error feedback and error averaging techniques.
result Our methods handle gradient mismatch and train faster than full-precision training.
Artificial neural networks with millions of adjustable parameters and a similar number of training examples are a potential solution for difficult, large-scale pattern recognition problems in areas such as speech and face recognition, classification of large volumes of web data, and finance. The bottleneck is that neur…
The paper clarifies the distinction between CATE and ITE under ignorability assumptions.
problem Confusion between CATE and ITE hinders personalized effect estimation.
method Clarifies the distinction between CATE and ITE under ignorability assumptions.
result CATE and ITE are not necessarily the same under ignorability assumptions.
A critical part of multi-person multi-camera tracking is person re-identification (re-ID) algorithm, which recognizes and retains identities of all detected unknown people throughout the video stream. Many re-ID algorithms today exemplify state of the art results, but not much work has been done to explore the deployme…
In causal inference, a variety of causal effect estimands have been studied, including the sample, uncensored, target, conditional, optimal subpopulation, and optimal weighted average treatment effects. Ad-hoc methods have been developed for each estimand based on inverse probability weighting (IPW) and on outcome regr…
In this paper we obtain three results concerning the geometry of complete noncompact positively curved Kähler manifolds at infinity. The first one states that the order of volume growth of a complete noncompact Kähler manifold with positive bisectional curvature is at least half of the real dimension (i.e., the complex…
Paper tackles imbalanced binary classification by optimizing precision and recall directly.
problem Imbalanced binary classification where standard accuracy is misleading.
method Exact constrained reformulations for precision and recall optimization.
result ERO framework outperforms state-of-the-art methods on multiple datasets.
Outlier detection methods have become increasingly relevant in recent years due to increased security concerns and because of its vast application to different fields. Recently, Pauwels and Lasserre (2016) noticed that the sublevel sets of the inverse Christoffel function accurately depict the shape of a cloud of data …
ASRI index detects crypto market risks with high precision and lead time.
problem Detecting systemic risks in cryptocurrency markets.
method Four weighted sub-indices (Stablecoin, DeFi, Contagion, Regulatory) validated against historical crises.
result ASRI detects significant abnormal signals with high statistical significance and lead time.
New insights into using momentum for non-convex optimization.
problem Improving training of non-convex models like deep neural networks.
method Developed a Lyapunov analysis of SGD with momentum using stochastic primal averaging.
result Precise conditions under which SGD+M outperforms SGD and optimal hyper-parameter schedules.
RF models implicitly regularize kernel methods as feature count increases.
problem Understanding implicit regularization in RF models.
method Random matrix theory applied to Gaussian RF models and KRR.
result The average RF predictor is close to a KRR predictor with an effective ridge.
Study on stochastic approximation with Polyak-Ruppert averaging for linear systems.
problem Understanding the asymptotic and non-asymptotic properties of stochastic approximation procedures.
method Detailed analysis of linear stochastic approximation with Polyak-Ruppert averaging, focusing on asymptotic and non-asymptotic properties.
result Proves CLT and non-asymptotic concentration inequality for averaged iterates, providing refined understanding of linear stochastic approximation.
The paper offers precise bounds for averaged LSA iterates in linear systems.
problem Computing approximate solutions of linear systems with noisy observations.
method Finite-time analysis of LSA algorithms with Polyak-Ruppert averaging.
result Sharp high-probability bounds for averaged LSA iterates.
Deep ROC analysis improves model selection and interpretation in medical and AI applications.
problem Inadequate performance measures for binary classifiers.
method Deep ROC analysis, translating AUC and partial AUC into balanced average accuracy and post-test measures.
result Deep ROC analysis provides balanced average accuracy, average sensitivity, and average specificity.
This paper provides new insight into maximizing F1 scores in the context of binary classification and also in the context of multilabel classification. The harmonic mean of precision and recall, F1 score is widely used to measure the success of a binary classifier when one class is rare. Micro average, macro average, a…
Massively multi-label prediction/classification problems arise in environments like health-care or biology where very precise predictions are useful. One challenge with massively multi-label problems is that there is often a long-tailed frequency distribution for the labels, which results in few positive examples for t…
Motivated by modern applications in which one constructs graphical models based on a very large number of features, this paper introduces a new class of cluster-based graphical models, in which variable clustering is applied as an initial step for reducing the dimension of the feature space. We employ model assisted cl…
New method combines multiple datasets to estimate ATE with valid confidence intervals.
problem Combining multiple observational datasets to estimate ATE with valid confidence intervals.
method Prediction-powered inferences to shrink CIs and provide valid CIs.
result Valid confidence intervals for ATE from multiple datasets.
Gaussian and bootstrap methods improve ATE estimator accuracy.
problem Improving the accuracy of Average Treatment Effect (ATE) estimators.
method Gaussian approximation and bootstrap procedures.
result Precise bounds on ATE estimator accuracy quantifying key parameters.
Novel AMP framework for multi-environment transfer learning.
problem Characterizing risk of Lasso-based transfer learning estimators.
method Multi-Environment Generalized Long AMP (multi-environment GLAMP) framework.
result Precise characterization of the risk of three Lasso-based transfer learning estimators.
We aim to predict and explain service failures in supply-chain networks, more precisely among last-mile pickup and delivery services to customers. We analyze a dataset of 500,000 services using (1) supervised classification with Random Forests, and (2) Association Rules. Our classifier reaches an average sensitivity of…