Study shows how information loss and operation loss are related in feature representations.
problem Understanding the relationship between information loss and operation loss in feature representations.
method Analyzes the interplay between weak information loss and operation loss in continuous representations.
result Specific forms of vanishing information loss imply vanishing MPE loss in classification.
Informer model with GMADL loss outperforms benchmarks in high frequency Bitcoin trading.
problem Developing automated trading strategies for high frequency Bitcoin data.
method Informer architecture with RMSE, GMADL, and Quantile loss functions.
result Informer model with GMADL loss function outperforms benchmarks in trading outcomes.
The paper decomposes probabilistic scores into reliability, uncertainty, and information loss.
problem Understanding the reliability and uncertainty of probabilistic predictions.
method Developed decomposition identities for proper losses, quantifying reliability, residual uncertainty, and information gain.
result A three-term identity for classification scores, revealing miscalibration, grouping term, and feature-level uncertainty.
Topology-enhanced loss improves 3D object reconstruction from 2D images.
problem Challenges in reconstructing 3D objects from 2D images, especially capturing shape information.
method Integrates multi-scale topological features into the reconstruction loss using cubical complexes and optimal transport distance.
result Topology-aware loss substantially improves 3D reconstruction quality.
We present and study a partial-information model of online learning, where a decision maker repeatedly chooses from a finite set of actions, and observes some subset of the associated losses. This naturally models several situations where the losses of different actions are related, and knowing the loss of one action p…
Forecastability measures predictive information across horizons.
problem How much predictive information is available at each prediction horizon?
method Develops the consequences of mutual information between future observations and information set.
result Forecastability is a profile reflecting process dependence structure, with properties like compression and truncation error.
New bounds on neural network test loss derived from conditional information measures.
problem Estimating test loss of neural networks trained on limited data.
method Framework based on conditional information density between hypothesis and training set.
result Tail bounds on test loss decay as 1/n, improving over previous 1/sqrt{n} bounds.
New PAC-Bayes method updates priors without losing confidence information.
problem Lack of sequential prior updates in PAC-Bayes without losing confidence information.
method Recursive PAC-Bayes decomposition of expected loss.
result Sequential prior updates with no information loss.
As financial instruments grow in complexity more and more information is neglected by risk optimization practices. This brings down a curtain of opacity on the origination of risk, that has been one of the main culprits in the 2007-2008 global financial crisis. We discuss how the loss of transparency may be quantified …
Cross-entropy loss linked to metric learning, outperforming complex pairwise losses.
problem Improving metric learning performance without complex optimization schemes.
method Theoretical analysis linking cross-entropy to pairwise losses, showing cross-entropy as an upper bound and equivalent to mutual information maximization.
result Minimizing cross-entropy is equivalent to maximizing mutual information, leading to state-of-the-art performance.
Anonymization reduces economic signal extraction from financial texts.
problem Reducing meaningful economic signals from financial texts due to anonymization.
method Analyzed the impact of anonymization on textual understanding and economic signal extraction.
result Information loss due to anonymization is severe and pervasive, outweighing its benefits in certain financial applications.
Typically, loss functions, regularization mechanisms and other important aspects of training parametric models are chosen heuristically from a limited set of options. In this paper, we take the first step towards automating this process, with the view of producing models which train faster and more robustly. Concretely…
DE-QT detects optimal Q-learning stopping points.
problem Information loss in Q-learning during prolonged training.
method Introducing DE-QT to detect entropy changes in Q-tables.
result DE-QT identifies the best stopping point for Q-learning.
Loss to followup is a significant issue in healthcare and has serious consequences for a study's validity and cost. Methods available at present for recovering loss to followup information are restricted by their expressive capabilities and struggle to model highly non-linear relations and complex interactions. In this…
We stabilize MI-based losses by adding a regularization term, improving their performance and stability.
problem Instability of MI-based losses in machine learning.
method Added a novel regularization term to stabilize MI-based losses.
result Regularization stabilizes training and improves the performance of MI-based losses.
Calibrating classifiers reduces grouping loss using sufficiency criteria.
problem Grouping loss in probabilistic classifier calibration is often overlooked.
method Revisited Langford & Zadrozny's probing reduction approach and introduced Brier curves.
result The probing reduction approach reduces grouping loss and supports sufficient calibration.
Boosting can efficiently optimize any loss function without requiring first-order information.
problem Boosting's efficiency in optimizing loss functions without first-order information.
method Extending gradient-based optimization to use only zeroth-order information.
result Boosting can optimize any loss function efficiently, including non-convex, non-differentiable, and non-continuous ones.
The performance of standard learning procedures has been observed to differ widely across groups. Recent studies usually attribute this loss discrepancy to an information deficiency for one group (e.g., one group has less data). In this work, we point to a more subtle source of loss discrepancy---feature noise. Our mai…
This paper considers the subject of information losses arising from the finite datasets used in the training of neural classifiers. It proves a relationship between such losses as the product of the expected total variation of the estimated neural model with the information about the feature space contained in the hidd…
Geodesics connect model modes in neural network loss landscapes.
problem Connecting modes in neural network loss landscapes.
method Reframed mode connectivity in Information Geometry, hypothesized geodesics as mode-connecting paths, proposed algorithm to approximate geodesics.
result Geodesics achieve mode connectivity in neural networks.
Paper proposes fitting loss functions to data using source functions from information geometry.
problem Choosing appropriate loss functions for machine learning models.
method Introduces source functions from information geometry to fit loss functions to the domain at hand.
result Significant improvements over state-of-the-art methods in model training.
A new method for survival analysis models that ensures fairness without using sensitive demographic data.
problem Ensuring fairness in survival analysis models without relying on sensitive demographic information.
method A worst-case error minimization approach using a training loss function that does not know sensitive demographic information.
result The proposed method often scores better on fairness metrics without a significant drop in prediction accuracy compared to baselines.
This paper improves traffic flow modeling by using multi-gradient descent algorithms for physics-informed machine learning.
problem Combining physics-based and data-driven approaches in traffic flow modeling.
method Introducing multi-gradient descent algorithms to explore the Pareto front in a multi-objective setting.
result Multi-gradient descent algorithms significantly outperform scalarization-based methods in complex PIML scenarios.
A new method for automatic gradient tree boosting using information theory.
problem Automatic selection of tree complexity and number in gradient boosting.
method Optimism of greedy leaf splitting procedure modeled as a Cox-Ingersoll-Ross process, leading to an information criterion for model selection.
result The method achieves significant speedups (10-1400) compared to xgboost without sacrificing predictive power.
New bounds using samplewise evaluated CMI for deep neural networks.
problem Improving generalization bounds for deep neural networks.
method Introduced a new family of information-theoretic generalization bounds using samplewise evaluated conditional mutual information (CMI).
result The new bounds can be tighter than previous ones for deep neural networks.
Sign information is the key to overcoming the inevitable saturation error in compressive sensing systems, which causes information loss and results in bias. For sparse signal recovery from saturation, we propose to use a linear loss to improve the effectiveness from existing methods that utilize hard constraints/hinge …
Sampling a fraction of pairs can match full evaluation in machine learning losses.
problem High computational cost of full pairwise loss evaluation.
method Survey sampling techniques targeting informative pairs.
result Performance close to full pairwise evaluation achieved with frugal sampling.
New methods evaluate data representations by complexity of low-loss predictor learning.
problem Evaluating quality of data representations for downstream tasks.
method Surplus Description Length (SDL) and ε Sample Complexity (εSC) methods.
result Methods measure the information needed to approximate optimal predictor up to specified tolerance.
Investors suffer welfare loss despite having better information.
problem Welfare loss among investors with absolute information advantages.
method Examined financial markets with heterogenous investors and objective measures of welfare.
result Investors incur welfare loss even with better information, revealing a double loss phenomenon.
In this paper, we present and illustrate some new tools for rigorously analyzing training data selection methods. These tools focus on the information theoretic losses that occur when sampling data. We use this framework to prove that two methods, Facility Location Selection and Transductive Experimental Design, reduce…
The study examines how formal index insurance compares to informal risk sharing in managing natural disasters.
problem The challenges of natural disasters and the effectiveness of index insurance in risk management.
method A three-strategy evolutionary game model to analyze the competitive relationship between formal index insurance, informal risk sharing, and non-insurance.
result Basis risk and loss ratio significantly impact the adoption rate of index insurance, with different strategies preferred under varying conditions.
Using established principles from Statistics and Information Theory, we show that invariance to nuisance factors in a deep neural network is equivalent to information minimality of the learned representation, and that stacking layers and injecting noise during training naturally bias the network towards learning invari…
This study examines fees in AMMs to reduce losses from informed orderflow.
problem Minimizing losses from informed orderflow in AMMs.
method Modeling arbitrage dynamics and sensitivity to fee choices.
result Identified fees that mimic price directionality to reduce losses.
New bounds derived for machine learning algorithms using convex functions.
problem Bounding generalization error in machine learning.
method Using strongly convex functions and subgaussian loss tails, derived new generalization bounds.
result Generalization bounds can be derived using any strongly convex function of the joint input-output distribution.
Optimal insurance contracts are designed to screen risk preferences and risk types under asymmetric information.
problem Designing optimal insurance contracts under asymmetric information and risk types.
method Constructing a menu of contracts that maximizes mean-variance utilities, subject to truth-telling constraints.
result Equilibrium contracts exhibit nonlinear pricing with decreasing risk loadings, inducing self-selection.
Poisson learning doesn't solve graph semi-supervised learning issues.
problem Global information loss in graph-based semi-supervised learning.
method Poisson learning is Laplace regularization with thresholding.
result Poisson learning cannot overcome the global information loss problem.
Ranking is a key aspect of many applications, such as information retrieval, question answering, ad placement and recommender systems. Learning to rank has the goal of estimating a ranking model automatically from training data. In practical settings, the task often reduces to estimating a rank functional of an object …
This paper proposes an alternative to E2E training for deep networks, reducing memory footprint.
problem High GPUs memory footprint in end-to-end training of deep networks.
method Locally supervised learning with information propagation loss to avoid information collapse.
result The proposed method achieves competitive performance with less than 40% memory footprint compared to E2E training.
Proposes a method to improve financial time series forecasting using compact representations and contrastive loss.
problem Financial time series forecasting with small datasets and overfitting issues.
method Class-conditioned latent variable model, mutual information maximization, contrastive loss, deep autoregressive models.
result Empirical experiments show improved performance compared to state-of-the-art methods.
Unified framework for expert selection with bandit and lower-bound feedback.
problem Selecting the best expert in scenarios with bandit feedback and lower-bound information.
method Introduces a new feedback model combining bandit and lower-bound information, proving optimal regret bounds for modified Exp3 algorithms.
result Optimal regret bounds for modified Exp3 algorithms, generalizing both bandit and full-information settings.
Study excess risk in statistical inference with transformations.
problem Excess risk in estimating random variables from feature vectors and transformations.
method Characterize lossless transformations, develop test statistics, and information-theoretic bounds.
result Strongly consistent partitioning test statistic for lossless transformations.
New GAN loss functions improve image generation quality and stability.
problem Improving the performance of GANs in generating high-quality images.
method Introducing least kth-order GAN (LkGAN) and Rényi-centric GAN loss functions. result The proposed loss functions lead to better image quality and stability.
Information-maximization clustering learns a probabilistic classifier in an unsupervised manner so that mutual information between feature vectors and cluster assignments is maximized. A notable advantage of this approach is that it only involves continuous optimization of model parameters, which is substantially easie…
Optimal sensor placement minimizes information loss from simulations.
problem Designing efficient sensor networks for spatiotemporal processes.
method Model-based sensor placement criterion with sparse variational inference and Gauss-Markov priors.
result Our method identifies sensor networks that minimize information loss from simulated data.
New theory improves understanding of ensemble learning systems.
problem Improving the effectiveness of ensemble learning systems.
method Generalized Fano's inequality to account for information loss in model combination.
result Reveals strengths and weaknesses of ensemble systems on accuracy and diversity.
New tighter bounds for learning algorithms from Steinke & Zakynthinou's supersample setting.
problem Improving generalization bounds for machine learning algorithms.
method Information-theoretic approach using projected loss and Rademacher sequence.
result The new bounds are tighter than previous information-theoretic bounds.
Study on privacy leakage in noisy gradient descent algorithms.
problem Information leakage of iterative randomized learning algorithms about training data.
method Analyzes the dynamics of Rényi differential privacy loss in noisy gradient descent algorithms.
result Privacy loss converges exponentially fast for smooth and strongly convex loss functions.
We investigate contextual online learning with nonparametric (Lipschitz) comparison classes under different assumptions on losses and feedback information. For full information feedback and Lipschitz losses, we design the first explicit algorithm achieving the minimax regret rate (up to log factors). In a partial feedb…