Improves bandit regret with small loss range, even with limited information.
problem Improving bandit regret with small loss range.
method Develops a novel technique to convert algorithms with regret depending on loss range to ones with regret depending only on effective range.
result Shows how to improve bandit regret guarantees with small loss range under certain assumptions.
A new method for forming learning objectives using the sum of ranked range.
problem Forming learning objectives from aggregated values.
method Sum of ranked range (SoRR) minimization with DCA.
result The proposed method effectively forms learning objectives and is applicable to binary and multi-label/multi-class classification.
Introduces SoRR for aggregating losses in supervised learning.
problem Aggregating individual losses into a single output for machine learning models.
method Sum of ranked range (SoRR) minimization using DCA.
result Demonstrates effectiveness of AoRR and TKML in improving robustness of multi-label learning.
Improved online learning algorithm for easy data with reduced regret.
problem Improving prediction accuracy with limited advice for easy data.
method Second Order Difference Adjustments (SODA) algorithm for online learning.
result Achieves improved regret guarantees for both stochastic and adversarial loss sequences.
Introduces CHL, a new loss function for continuous similarity learning.
problem Binary similarity learning limitations.
method CHL is a novel loss function that generalizes histogram loss to continuous similarities.
result CHL solves a wider range of tasks including similarity learning, representation learning, and data visualization.
New PAC-Bayes bounds for unbounded loss functions.
problem Generalization bounds for learning problems with unbounded loss functions.
method Introducing HYPE, a new notion for loss range, and deriving a novel PAC-Bayesian generalization bound.
result PAC-Bayes framework extended to unbounded loss functions.
EnsLoss combines multiple loss functions to prevent overfitting in classification.
problem Preventing overfitting in classification models.
method EnsLoss is an ensemble method that combines loss functions, ensuring calibration and consistency.
result EnsLoss improves classification accuracy compared to fixed loss methods.
Efficient algorithm reduces online multiclass prediction regret to sqrt(T).
problem Online multiclass prediction with bandit feedback.
method Second-order algorithm with regret bound of O(1/η√T).
result Regret bound holds for a range of loss functions.
Paper optimizes liquidity provision in decentralized finance markets.
problem Strategic LPs face predictable losses and concentration risk in CL pools.
method Derive optimal liquidity provision strategy based on fees, PL, and concentration risk.
result Optimal strategy increases fee revenue and profit from marginal rate changes.
Adma proposes a flexible loss function for neural networks.
problem Static loss functions limit neural network performance.
method Introduces a flexible loss function that adapts to ANN complexity and data distribution.
result Flexible loss function achieves state-of-the-art performance.
Unified theory explains diversity in ensemble learning.
problem Explaining diversity in ensemble learning across various scenarios.
method Developed a framework revealing diversity as a hidden dimension in bias-variance decomposition.
result Proved exact bias-variance-diversity decompositions for multiple losses in regression and classification.
New loss function improves accuracy of MRI parameter estimation.
problem Systematic errors in parameter estimates at low SNR.
method Developed and implemented negative log Rician likelihood (NLR) loss.
result NLR loss shows higher accuracy in parameter estimation than MSE loss at low SNR.
Model learns disentangled frames from video, enabling future frame prediction.
problem Learning disentangled representations from video sequences.
method Temporal coherence and adversarial loss for disentanglement.
result Model can predict future frames coherently.
We analyze bias-variance of margin losses.
problem Understanding model overfitting/underfitting.
method Bias-variance decomposition for strictly convex margin losses.
result Expected risk decomposes into central model risk and data variation.
Analyzes impermanent loss in decentralized exchanges and provides a replication formula.
problem Impermanent loss in decentralized exchanges like Uniswap and Balancer.
method Analytical static replication formula using European calls and puts.
result Guaranteed coverage for pool value within a predefined range.
Procedure optimizes default thresholds to minimize financial loss in credit risk scenarios.
problem Finding the optimal default threshold to minimize financial loss in loan portfolios.
method Objective comparison and evaluation of default definitions using optimisation procedure.
result Loss minima can exist for a select range of credit risk profiles, suggesting loss optimisation of default thresholds is viable.
SGLB boosts machine learning with Langevin diffusion for multimodal loss functions.
problem Dealing with multimodal loss functions in machine learning.
method Stochastic Gradient Langevin Boosting (SGLB) based on Langevin diffusion equation.
result SGLB guarantees global convergence for multimodal loss functions.
This paper explores neural network loss landscapes and their effects on generalization.
problem Understanding the structure of neural network loss functions and their impact on generalization.
method Simple filter normalization and various visualization methods to explore loss landscape structure and network architecture effects.
result Visualizations reveal how network architecture and training parameters affect loss landscape curvature and minimizers.
We use barcodes to analyze neural networks' loss surfaces, revealing important properties.
problem Understanding the topology of neural networks' loss surfaces.
method Topological data analysis using Morse complexes and barcodes.
result Barcodes of local minima are located in a small part of the loss function's range and decrease with network depth and width.
CrossTrainer adapts models across diverse datasets using loss reweighting.
problem Training models with data from varying sources or of varying quality.
method Loss reweighting with optimizations for hyperparameter tuning.
result High model accuracy across various datasets with improved training time.
Adaptive loss function improves performance by aligning training and evaluation metrics.
problem Loss-metric mismatch in machine learning training.
method Adaptive loss alignment through meta-learning of a dynamic loss function.
result Significant performance improvements across various tasks and data.
Unified binary and multiclass margin-based classification methods.
problem No consensus on multiclass loss functions analogous to binary margin loss.
method Showed multiclass loss functions can be expressed in relative margin form.
result Extended classification-calibration result to multiclass.
Improved music source separation using spectrogram feature loss.
problem Music source separation quality improvement.
method Added a high-level feature loss term from spectrograms using a VGG net to a deep learning model.
result Improvement in separation quality of drums and vocals from songs.
Two algorithms minimize regret in adversarial bandit problems with side-observation losses.
problem Minimizing regret in adversarial multi-armed bandit problems with side-observation losses.
method Proposes two algorithms for different ranges of side-observation probability.
result Regret bounds for different values of side-observation probability.
This work generalizes calibeating for a broader range of proper losses using Bregman divergence.
problem Calibration for a wide range of proper losses beyond Brier and log loss.
method Regret minimization based on Bregman divergence for a family of proper losses.
result U-calibration results for a family of Tsallis losses with logarithmic regret and dimension independence.
Catapult phase in neural nets shows exponential loss growth before quick decrease.
problem Understanding phase transitions in neural networks during training.
method Analyzing weight norm and loss behavior for super-critical learning rates.
result Proven existence of catapult phase in quadratic models and two-layer nets.
Study tackles criterion collapse in learning criteria, showing conditions for loss minimization.
problem Criterion collapse in optimization, focusing on error probability minimizers.
method Analyzes various learning criteria, including DRO, OCE risks, and non-monotonic criteria.
result Non-monotonic criteria can avoid collapse, while monotonic ones cannot.
New methods for quantifying insurance claim cost uncertainty using LightGBM and GLMs.
problem Quantifying prediction uncertainty in insurance claim costs.
method Proposed non-conformity measures for GLMs and GBMs with Tweedie loss.
result Locally weighted Pearson residuals outperform other methods in maintaining nominal coverage with smallest average width.
Study shows AMM liquidity providers lose more than they earn, with varying profitability across pairs.
problem Arbitrage losses by liquidity providers on AMMs exceed fees earned.
method Empirical study of losses and profitability across different AMM pools and block times.
result Uniswap v2 pools are more profitable for passive LPs than Uniswap v3.
GANs can generate realistic data without minimizing a divergence, contrary to current theory.
problem Current theory suggests GANs minimize a divergence to generate realistic data.
method Discussed various loss functions for G, showing they are not divergences and do not have the same equilibrium.
result GANs can use a wide range of loss functions, not just divergences, to generate realistic data.
Unified algorithm for tensor decomposition supports multiple loss functions and models.
problem Efficient tensor decomposition for various models and loss functions.
method Hierarchical combination of ADMM and MM for optimization.
result Wide-range applications can be solved by the proposed algorithm.
Study extreme-case Value-at-Risk under IFR distributions, providing guidance for risk management.
problem Understanding extreme-case risk measures under distributional ambiguity and increasing failure rate.
method Characterized extreme-case range Value-at-Risk under mean and variance constraints with increasing failure rate.
result Characterized specific characteristics of extreme-case distributions under IFR constraints.
This paper introduces the hypervolume maximization with a single solution as an alternative to the mean loss minimization. The relationship between the two problems is proved through bounds on the cost function when an optimal solution to one of the problems is evaluated on the other, with a hyperparameter to control t…
Optimizes partial AUC across various FPRs for machine learning models.
problem Lack of scalable algorithms for optimizing partial AUC in a range of FPRs.
method Formulated as a non-smooth DC program, developed an efficient approximated gradient descent method using Moreau envelope smoothing.
result Achieved a complexity of O(1/ε6) for finding nearly ε-critical solutions. Paper proposes transparent insurance models for PBMs.
problem PBMs' opaque business models and hidden profits.
method Quantitative estimates of two models with fixed premiums and fee-for-service.
result Proposes transparent models with fixed premiums and fee-for-service.
New method reduces memory usage in deep HRNNs by replacing gradient backpropagation with local losses.
problem Memory constraints in training deep hierarchical RNNs.
method Replace gradient backpropagation with locally computable losses in deep HRNNs.
result Memory requirements reduced by a factor exponential in hierarchy depth.
Study minimax rates for density estimation under Huber contamination and Besov IPM losses.
problem Minimax convergence rates of nonparametric density estimation under Huber contamination model with outliers.
method Re-scaled thresholding wavelet series estimator and GAN architectures.
result Achieves minimax optimal convergence rates under Besov IPM losses.
New expressive losses improve adversarial robustness without sacrificing accuracy.
problem Training networks for robustness at the expense of accuracy.
method Formalizing expressivity, using convex combinations of adversarial attacks and IBP bounds.
result Trivial expressive losses yield state-of-the-art results in various settings.
HGNet improves GNNs' ability to handle long-range interactions in graphs.
problem Insufficiency of GNNs in capturing long-range interactions.
method Introduces hierarchical message passing models with multi-resolution graph representations.
result HGNet outperforms conventional GNNs in molecular property prediction.
Paper develops estimators for unbounded density ratios with applications in error control.
problem Estimating density ratios with unbounded domains and ranges.
method Least squares and logistic regression loss functions for density ratio estimation.
result Established upper bounds on estimation errors with optimal rates for unbounded density ratios.
Paper improves PAC-Bayes bounds for various loss types.
problem Improving PAC-Bayes bounds for different types of losses.
method Introducing new high-probability PAC-Bayes bounds for bounded and general tail behaviors losses, and extending to anytime-valid bounds.
result New fast-rate and mixed-rate bounds for losses with bounded ranges, and parameter-free bounds for losses with general tail behaviors.
Paper quantifies distortion risk measures' robustness to distributional uncertainty.
problem Quantifying risk measures' robustness to distributional uncertainty.
method Employing isotonic projections, the paper derives bounds on distortion risk measures' values.
result Sharp bounds on distortion risk measures' values are provided, especially for Value-at-Risk and Range-Value-at-Risk.
EGFs use ergodicity to simplify generative flows for easier training and imitation learning.
problem Challenges in training generative flows, especially in continuous settings and for imitation learning.
method EGFs leverage ergodicity to build simple flows with universality guarantees and tractable FM loss. They introduce a KL-weakFM loss for IL training without a separate reward model.
result EGFs simplify generative flow training and enable effective imitation learning.
Enhances linear regression with Kalman filter for loss minimization.
problem Minimizing loss in linear regression models.
method Integrates Kalman filter and SGD for optimal weight updates.
result Develops optimal linear regression equation with minimum area under curve.
The paper proves neural networks' consistency and optimal convergence rates for various function classes.
problem Proving neural networks' consistency and optimal convergence rates for diverse function classes.
method Analyzes wide and deep ReLU neural networks trained on logistic loss and Kolmogorov-Donoho optimal function classes.
result Proves universal consistency and minimax optimal convergence rates for neural networks.
New method simplifies checking consistency of differentiable loss functions.
problem Verifying consistency of differentiable loss functions is difficult.
method Developed a new approach called strong indirect elicitation (strong IE) to simplify checking consistency.
result Strong IE is equivalent to calibration for strongly convex, differentiable surrogates.
GCML preserves geometric structure in manifold clustering for diverse data types.
problem Loss functions in manifold clustering can corrupt latent space structure.
method GCML framework with isometric and ranking losses for geometric structure preservation.
result GCML outperforms other methods in latent space structure preservation and performance metrics.
We found a 'Goldilocks zone' in neural network loss landscapes that correlates with good initialization.
problem Understanding and optimizing neural network loss landscapes for better initialization.
method Random and low-dimensional hypersurfaces to evaluate the Hessian of loss functions.
result The Goldilocks zone is a region of unusually high convexity and positive curvature, correlated with good network performance.