Loss-calibrated EP improves Bayesian decision-making by focusing on utility-sensitive posterior approximations.
problem Bayesian decision-making under asymmetric utility functions.
method Loss-calibrated expectation propagation (Loss-EP) that tilts the posterior towards higher utility decisions.
result Loss-EP can capture useful information for decision-making under asymmetric penalties.
Paper introduces arctan pinball loss for XGBoost quantile regression.
problem Efficiently predicting multiple quantiles with XGBoost.
method Smooth approximation of pinball loss for XGBoost, using arctan pinball loss.
result Arctan pinball loss reduces quantile crossings and improves efficiency.
SIFT reduces training time by selecting samples with approximate losses.
problem Reducing training time by selecting samples with large approximate losses.
method Developed SIFT which uses early exiting to obtain approximate losses with intermediate layer representations for sample selection.
result SIFT achieves significant gains in training time and number of backpropagation steps without optimized implementation.
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.
Unified framework approximates gradient descent's implicit bias in high dimensions.
problem Understanding gradient descent's behavior in overparameterized settings with convex losses.
method Unified framework for convex losses, including sensitivity analysis.
result Approximation of minimum-norm interpolation in high dimensions.
A new method for exponentially weighted moving models using approximations.
problem Efficiently updating moving averages for time series data.
method Approximates EWMM using a fixed window and quadratic term, solving non-growing problems.
result Approximation produces estimates similar to exact EWMM.
The impact of a stress scenario of default events on the loss distribution of a credit portfolio can be assessed by determining the loss distribution conditional on these events. While it is conceptually easy to estimate loss distributions conditional on default events by means of Monte Carlo simulation, it becomes imp…
We prove a law of large numbers for the loss from default and use it for approximating the distribution of the loss from default in large, potentially heterogenous portfolios. The density of the limiting measure is shown to solve a non-linear SPDE, and the moments of the limiting measure are shown to satisfy an infinit…
This paper concerns a method of selecting a subset of features for a sequential logit model. Tanaka and Nakagawa (2014) proposed a mixed integer quadratic optimization formulation for solving the problem based on a quadratic approximation of the logistic loss function. However, since there is a significant gap between …
This work tackles Bayesian neural networks by addressing loss landscape symmetries.
problem Understanding and optimizing the loss landscape of Bayesian neural networks.
method The approach involves extending marginalized loss barrier formalism to BNNs, proposing a matching algorithm to search for linearly connected solutions using permutation matrices and combinatorial optimization.
result Nearly zero marginalized loss barriers for linearly connected solutions were found.
A new method approximates expected empirical loss for stochastic deep learning tasks.
problem Determining optimal step sizes for stochastic gradient descent in deep learning.
method Applying one-dimensional function fitting to noisy losses of vertical cross sections to approximate expected empirical loss.
result The method leads to a robust and straightforward optimization method that performs well across datasets and architectures.
We analyze the fluctuation of the loss from default around its large portfolio limit in a class of reduced-form models of correlated firm-by-firm default timing. We prove a weak convergence result for the fluctuation process and use it for developing a conditionally Gaussian approximation to the loss distribution. Nume…
This paper proposes a new methodology to compute Value at Risk (VaR) for quantifying losses in credit portfolios. We approximate the cumulative distribution of the loss function by a finite combination of Haar wavelets basis functions and calculate the coefficients of the approximation by inverting its Laplace transfor…
Proposes sigmoidF1 loss for multilabel classification, improving performance metrics.
problem Lack of smooth, tractable loss functions for multilabel classification.
method Introduces sigmoidF1, a smooth F1 score surrogate loss function.
result sigmoidF1 outperforms other loss functions on various datasets and metrics.
New PG losses improve decision optimization in misspecified models.
problem Improving decision optimization in models that are not perfectly specified.
method Introducing Perturbation Gradient (PG) losses to connect decision loss with directional derivatives and optimizing using gradient techniques.
result PG losses yield best-in-class policies asymptotically, even in misspecified settings.
Fine-grained analysis of gradient descent with momentum provides modified loss equations.
problem Understanding the dynamics of gradient descent with momentum.
method Fine-grained analysis and derivation of modified loss equations.
result Global approximation bounds and continuous modified equations for HB.
Study visualizes actor-critic loss landscapes for inventory optimization.
problem Difficulties in solving multi-store dynamic inventory control problems.
method Low-dimensional visualizations of actor loss function.
result Loss landscapes favor optimal policies in reinforcement learning.
The paper corrects Bayesian neural network approximations to improve decision quality.
problem Inaccurate posterior approximations in Bayesian neural networks lead to suboptimal decisions.
method Develops methods to calibrate approximate posterior predictive distributions for better decision making.
result Empirically produces higher quality decisions compared to previous methods.
We set the context for capital approximation within the framework of the Basel II / III regulatory capital accords. This is particularly topical as the Basel III accord is shortly due to take effect. In this regard, we provide a summary of the role of capital adequacy in the new accord, highlighting along the way the s…
Gradient descent struggles to achieve zero loss in deep learning models due to non-generic data distributions.
problem Achieving zero loss minimizers in deep learning networks.
method Analysis of gradient descent algorithm in deep learning, focusing on underparametrized networks.
result Zero loss minimization cannot be achieved generically in deep learning networks.
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.
We describe an approximate dynamic programming (ADP) approach to compute approximations of the optimal strategies and of the minimal losses that can be guaranteed in discounted repeated games with vector-valued losses. Such games prominently arise in the analysis of regret in repeated decision-making in adversarial env…
This paper establishes the asymptotic consistency of the {\it loss-calibrated variational Bayes} (LCVB) method. LCVB was proposed in~\cite{LaSiGh2011} as a method for approximately computing Bayesian posteriors in a `loss aware' manner. This methodology is also highly relevant in general data-driven decision-making con…
New method approximates curvature from symmetries in deep networks.
problem Hard to approximate curvature in large deep networks.
method Analytically averaging over group actions that leave the loss invariant to construct structured Hessian approximations.
result Structured Hessian approximations from single gradients can be estimated, stored, and inverted.
Proposes a method for inference in high-dimensional classification with non-differentiable surrogate losses.
problem Lack of inference procedures for identifying driving factors in high-dimensional classification with non-differentiable surrogate losses.
method Kernel-smoothed decorrelated score and cross-fitted version for hypothesis tests and interval estimators.
result Valid and superior inference methods for high-dimensional classification with non-differentiable surrogate losses.
Proposes variational Gaussian approximations for solving the Kushner equation.
problem Solving the Kushner equation for state estimation with observations.
method Tractable variational Gaussian approximations of proximal losses based on Wasserstein and Fisher metrics.
result The proposed method leads to a Gaussian flow consistent with Kalman-Bucy and Riccati flows.
We obtain the first positive results for bounded sample compression in the agnostic regression setting with the ℓp loss, where p∈[1,∞]. We construct a generic approximate sample compression scheme for real-valued function classes exhibiting exponential size in the fat-shattering dimension but independen…
Current approaches in approximate inference for Bayesian neural networks minimise the Kullback-Leibler divergence to approximate the true posterior over the weights. However, this approximation is without knowledge of the final application, and therefore cannot guarantee optimal predictions for a given task. To make mo…
The predictive quality of machine learning models is typically measured in terms of their (approximate) expected prediction accuracy or the so-called Area Under the Curve (AUC). Minimizing the reciprocals of these measures are the goals of supervised learning. However, when the models are constructed by the means of em…
The Nyström method improves learning efficiency for convex losses.
problem Improving computational efficiency in empirical risk minimization.
method Using random subspaces to approximate hypothesis spaces in convex loss functions.
result Computational gains can be achieved without sacrificing learning performance for general convex Lipschitz losses.
We present an easily implemented, fast, and accurate method for approximating extreme quantiles of compound loss distributions (frequency+severity) as are commonly used in insurance and operational risk capital models. The Interpolated Single Loss Approximation (ISLA) of Opdyke (2014) is based on the widely used Single…
A new federated learning algorithm improves on existing methods by exploiting data smoothness.
problem Federated learning optimization with smooth loss functions.
method Federated Low Rank Gradient Descent (FedLRGD) algorithm.
result FedLRGD outperforms Federated Averaging (FedAve) in federated oracle complexity under certain conditions.
Gradient-based methods find saddle points, not critical points, in neural networks.
problem Gradient-based optimization methods converge to saddle points rather than critical points in deep neural networks.
method Critical point-finding methods used to analyze neural network losses.
result Gradient-based methods often converge to or pass through gradient-flat regions, where gradient norm has a stationary point.
Efficiently learns Single-Index Models with constant factor approximation.
problem Learning Single-Index Models under L22 loss with unknown link functions. method An efficient algorithm using alignment sharpness for optimization.
result Achieves constant factor approximation to optimal loss for various distributions and link functions.
Uniform diffusion approximation for SGD in non-convex settings.
problem Finite-time diffusion approximation for SGD.
method Establishing uniform-in-time diffusion approximation with strong convexity and mild conditions.
result Uniform-in-time diffusion approximation of SGD without convexity of each loss function.
Wasserstein GANs fail to approximate Wasserstein distance, leading to their success.
problem Approximating Wasserstein distance in deep generative models.
method Analysis of differences between theoretical setup and training reality.
result Wasserstein GANs' success is due to their failure to approximate Wasserstein distance.
New method achieves small-loss regret bounds in random-order model.
problem Online learning with adversarial loss functions in random order.
method Extending batch-to-online transformation, using average sensitivity and stability.
result Small-loss regret bounds of order ildeO(φ⋆(OPTT)). Simplified plug-in loss approximates EDL for reliable uncertainty estimation.
problem Efficient and reliable uncertainty estimation in real-world sensor-based learning systems.
method Approximate Dirichlet expected objectives with plug-in losses evaluated at the Dirichlet mean.
result Plug-in losses provide comparable predictive accuracy and selective prediction performance to classical EDL, while being simpler to implement.
In this paper we revisit the weighted likelihood bootstrap, a method that generates samples from an approximate Bayesian posterior of a parametric model. We show that the same method can be derived, without approximation, under a Bayesian nonparametric model with the parameter of interest defined as minimising an expec…
Develops a new framework for robust regression with EGM.
problem Addressing robust regression with heavy-tailed noise or outliers.
method Empirical gain maximization (EGM) to approximate noise density.
result Unified analysis of robust regression approaches.
A major challenge in current optimization research for deep learning is to automatically find optimal step sizes for each update step. The optimal step size is closely related to the shape of the loss in the update step direction. However, this shape has not yet been examined in detail. This work shows empirically that…
Paper addresses ERM in LDP, reducing sample complexity for smooth and convex losses.
problem Achieving error α in ERM with non-interactive LDP, especially for high-dimensional data.
method Developed algorithms using Bernstein polynomial and polynomial approximation techniques.
result For smooth and convex losses, sample complexity is linear in dimensionality.
Sobolev training helps neural nets fit function values and derivatives.
problem Training neural nets to match function values and derivatives accurately.
method Using Sobolev loss with gradient flow for overparameterized networks.
result Gradient flow from random initialization can fit any function and its derivatives.
We study the column subset selection problem with respect to the entrywise ℓ1-norm loss. It is known that in the worst case, to obtain a good rank-k approximation to a matrix, one needs an arbitrarily large nΩ(1) number of columns to obtain a (1+ε)-approximation to the best entrywise ℓ1-norm low ra…
A new method automatically and dynamically sets learning rates in deep learning.
problem Determining the appropriate learning rate in deep learning tasks is challenging and often subjective.
method Local Quadratic Approximation (LQA) to automatically and dynamically set learning rates.
result The proposed method leads to nearly optimal learning rates in a computationally efficient way.
In this paper we study a class of insurance products where the policy holder has the option to insure k of its annual Operational Risk losses in a horizon of T years. This involves a choice of k out of T years in which to apply the insurance policy coverage by making claims against losses in the given year. The…
We introduce a "learning-based" algorithm for the low-rank decomposition problem: given an n×d matrix A, and a parameter k, compute a rank-k matrix A′ that minimizes the approximation loss ∥A−A′∥F. The algorithm uses a training set of input matrices in order to optimize its performance. Specifical…
Study non-asymptotic bounds for robust estimators under misspecified models.
problem Evaluate performance of robust estimators under adversarial conditions.
method Propose a general approach to adversarial risk analysis, including investigations on generalization and approximation errors.
result Establish non-asymptotic upper bounds for adversarial excess risk under Lipschitz loss functions.