We analyze how uncertainty in models affects optimization outcomes using Wasserstein distances.
problem Sensitivity of optimization problems to model uncertainty.
method Non-parametric approach using Wasserstein balls to capture uncertainty, providing explicit corrections for value function and optimizer.
result Explicit formulae for first-order corrections to value function and optimizer.
Researchers quantify risk exposure and sensitivities in financial markets under model uncertainty.
problem Optimizing investment and pricing under model uncertainty in financial markets.
method Distributionally robust optimization, Wasserstein ball, first-order sensitivity analysis.
result Sensitivities of value function, investment policy, and marginal prices to model uncertainty can be non-monotonic.
Study examines how slight model changes affect multi-period optimization outcomes.
problem Effect of small probabilistic model changes on multi-period optimization problems.
method Adapted Wasserstein distance for measuring changes, explicit first-order approximations proved.
result Explicit first-order approximations for multi-period stochastic optimization and optimal stopping problems.
Risk management in financial derivative markets requires inevitably the calculation of the different price sensitivities. The literature contains an abundant amount of research works that have studied the computation of these important values. Most of these works consider the well-known Black and Scholes model where th…
New Monte Carlo method outperforms existing strategy for estimating Sobol' indices.
problem Estimating first-and total-orders Sobol' indices accurately.
method Comparing two Monte Carlo estimators for Sobol' indices.
result New method outperforms current approach in accuracy.
Cost-Sensitive Online Classification has drawn extensive attention in recent years, where the main approach is to directly online optimize two well-known cost-sensitive metrics: (i) weighted sum of sensitivity and specificity; (ii) weighted misclassification cost. However, previous existing methods only considered firs…
The paper calculates option prices using Mellin transform for stochastic volatility models.
problem Calculating prices for path-dependent options under stochastic volatility.
method Asymptotic approach and Mellin transform for deriving closed-form formulas.
result Derives closed-form formulas for option prices with first-order approximation.
CEFOL uses deep learning for dynamic programming with recursive utility.
problem Challenges in solving dynamic programming problems with recursive utility.
method Introduces a separate neural network for certainty equivalent, uses first-order optimality conditions to learn value and policy functions.
result CEFOL achieves high accuracy in learning value and policy functions, matching VFI benchmarks.
We study the sensitivity of the expected utility maximization problem in a continuous semi-martingale market with respect to small changes in the market price of risk. Assuming that the preferences of a rational economic agent are modeled with a general utility function, we obtain a second-order expansion of the value …
Investigates model risk and semi-static hedging for martingale constrained models.
problem Model risk distributionally robust sensitivities for functionals on the Wasserstein space.
method Introduces distributionally robust problem with semi-static hedging strategies.
result Explicit characterizations of model risk optimal semi-static hedging strategies.
Optimizer memory affects learning rate sensitivity in shuffle order, impacting fine-tuning noise.
problem Optimizer memory affects the learning rate sensitivity in shuffle order, leading to fine-tuning noise.
method Isolated the mechanism of fixed-clock optimizer memory affecting the learning rate sensitivity in shuffle order, deriving a fit-free way to size the noise.
result Fixed-clock optimizers like AdamW produce a larger first-order noise channel compared to memoryless optimizers, affecting fine-tuning comparisons.
SONODEs and ANODEs improve learning of second order dynamics.
problem Learning dynamics governed by second order laws.
method Extended adjoint sensitivity method and theoretical analysis of ANODEs.
result SONODEs and ANODEs can learn higher order dynamics efficiently.
Parallel computing has played an important role in speeding up convex optimization methods for big data analytics and large-scale machine learning (ML). However, the scalability of these optimization methods is inhibited by the cost of communicating and synchronizing processors in a parallel setting. Iterative ML metho…
Paper proposes a new method to measure model sensitivity using final model only.
problem Understanding model behavior using only the final trained model.
method Reframe TDA as measuring sensitivity, propose further training as gold standard, unify gradient-based methods.
result Gradient-based methods approximate further training but vary in quality.
Proposes a new OAL algorithm for imbalanced data with limited labels.
problem Handling imbalanced unlabeled datastream with limited query budget.
method Integrates asymmetric losses and queries strategies, uses second-order optimization, and applies sketching technique.
result Demonstrates improved performance and efficiency in class imbalance.
Proposes a fair PCA algorithm that balances reconstruction loss and fairness.
problem PCA can be unfair to different groups.
method Adaptive first-order algorithm for Pareto optimality.
result The algorithm finds a fair subspace that minimizes reconstruction loss.
Emulator speeds up landslide run-out modeling sensitivity analysis.
problem Computational challenges in assessing landslide run-out model sensitivity.
method Gaussian process emulation integrated into r.avaflow.
result Strong interactions detected between friction coefficients and release volume.
Study a continuous-time PA problem with private effort and consumption decisions.
problem Continuous-time Principal-Agent problem with private information.
method Proposes a new sufficient condition for solving the agent's problem directly.
result Directly yields a solution to the agent's problem without verification.
It is an open question whether there are Vassiliev invariants that can distinguish an oriented knot from its inverse, i.e., the knot with the opposite orientation. In this article, an example is given for a first order Vassiliev invariant that takes different values on a virtual knot and its inverse. The Vassiliev inva…
With the growth of renewable generation (RG) and the development of associated ride through curves serving as operating limits, during disturbances, on violation of these limits, the power system is at risk of losing large amounts of generation. In order to identify preventive control measures that avoid such scenarios…
The paper explores how different loss functions impact reinforcement learning algorithms.
problem Improving reinforcement learning algorithms by optimizing loss functions.
method Comprehensive survey on loss functions in reinforcement learning, proving the benefits of specific loss functions.
result Binary cross-entropy loss leads to first-order bounds and is more efficient than squared loss.
A cornerstone of human statistical learning is the ability to extract temporal regularities / patterns from random sequences. Here we present a method of computing pattern time statistics with generating functions for first-order Markov trials and independent Bernoulli trials. We show that the pattern time statistics c…
Geometric approach to thermodynamics of chemical reaction networks.
problem Thermodynamics of chemical reaction networks with non-ideal behavior.
method Information geometry, Riemannian geometry, Cramer-Rao bound, absolute sensitivity.
result Absolute sensitivity is a projection operator onto the tangent bundle of the equilibrium manifold.
Researchers use information geometry to analyze and improve DRWs for node classification.
problem Lack of theoretical foundations for Discriminative Random Walks (DRWs).
method Revisit DRWs through information geometry, treating hitting-time laws as a statistical manifold. Derived closed-form expressions and introduced sensitivity scores.
result Introduced a sensitivity score that bounds maximal first-order change in DRW betweenness under unit Fisher perturbations.
We address online combinatorial optimization when the player has a prior over the adversary's sequence of losses. In this framework, Russo and Van Roy proposed an information-theoretic analysis of Thompson Sampling based on the information ratio, resulting in optimal worst-case regret bounds. In this paper we introduce…
Machine learning algorithms have been increasingly deployed in critical automated decision-making systems that directly affect human lives. When these algorithms are only trained to minimize the training/test error, they could suffer from systematic discrimination against individuals based on their sensitive attributes…
NDDV estimates data point value from a single stochastic trajectory.
problem Estimating marginal contributions of data points over stochastic training paths.
method Introduces Neural Dynamic Data Valuation (NDDV) using stochastic state and adjoint equations.
result NDDV provides a one-run, trajectory-conditioned estimator of data point value.
This paper provides a set of sensitivity analysis and activity identification results for a class of convex functions with a strong geometric structure, that we coined "mirror-stratifiable". These functions are such that there is a bijection between a primal and a dual stratification of the space into partitioning sets…
Most neural networks are trained using first-order optimization methods, which are sensitive to the parameterization of the model. Natural gradient descent is invariant to smooth reparameterizations because it is defined in a coordinate-free way, but tractable approximations are typically defined in terms of coordinate…
Proposes second-order influence functions for identifying influential groups in test-time predictions.
problem Identifying influential groups in test-time predictions for black-box models.
method Second-order approximations of the effect of removing a group of training samples on model predictions.
result Improves the correlation between computed influence values and ground truth values for linear models.
In the general framework of a semimartingale financial model and a utility function U defined on the positive real line, we compute the first-order expansion of marginal utility-based prices with respect to a ``small'' number of random endowments. We show that this linear approximation has some important qualitative …
Paper proposes an efficient online Newton method with Nesterov's acceleration for streaming data.
problem Efficient inference of online Newton methods with robustness to noise and ill-conditioning.
method Online Newton method with Hessian averaging and Nesterov's accelerated sketch-and-project solver.
result Global almost-sure convergence and asymptotic normality of the last iterate with non-asymptotic convergence guarantees.
Examines how first-order differential operators can be equivalently transformed.
problem Equivalence of first-order linear differential operators.
method Discussion of equivalency transformations.
result Explains how first-order differential operators can be transformed equivalently.
New vector fields integrate first-order ODEs.
problem Integrating first-order ODEs.
method Relation between Riemannian manifolds and ODEs integration.
result Integration procedure for first-order ODEs.
Study first-order locally convex Lie algebroids in Bastiani calculus.
problem Define and study first-order locally convex Lie algebroids.
method Define sheaves of Lie algebroid forms and morphisms, prove category structure, study representations and cohomology.
result First-order locally convex Lie algebroids form a category and have applications in Lie II theorems.
New metric derived for robust optimization in stochastic control problems.
problem Non-parametric uncertainty in multiperiod stochastic control problems.
method Derived a new metric, adapted (p,∞)--Wasserstein distance, and used dynamic programming principle. result Dynamic programming principle for DRO problems with semi-separable cost functions.
A new method solves complex constrained minimax problems.
problem Solving constrained minimax optimization problems.
method First-order augmented Lagrangian method.
result Established an operation complexity of O(ε−4logε−1). A guide for solving first-order elliptic boundary value problems.
problem Solving first-order elliptic boundary value problems on manifolds.
method Operator methods and general elliptic boundary conditions.
result Characterization of a new subclass of elliptic boundary conditions.
We study the out-of-sample properties of robust empirical optimization problems with smooth φ-divergence penalties and smooth concave objective functions, and develop a theory for data-driven calibration of the non-negative "robustness parameter" δ that controls the size of the deviations from the nominal model. Bu…
Improved private geometric median estimation with nearly-linear time complexity.
problem Estimating the geometric median of a dataset while maintaining privacy.
method Improved algorithm using subsampling and geometric aggregation, achieving nearly-linear runtime.
result Achieves the same approximation quality as previous methods but with nearly-linear runtime.
First-order ODEs linked to flat surfaces, leading to integrability.
problem Integrating first-order ODEs.
method Defined Riemannian metrics on variable spaces, studied surface properties, and established connections between Jacobi fields and Lie point symmetries.
result Flat associated surfaces lead to integrable first-order ODEs.
Extends a theorem for first-order elliptic operators on manifolds.
problem Proving the relative index theorem for general first-order elliptic operators.
method Using boundary value problems and graphical decomposition of elliptically regular boundary conditions.
result Proves the relative index theorem for general first-order elliptic operators.
Two classes of methods have been proposed for escaping from saddle points with one using the second-order information carried by the Hessian and the other adding the noise into the first-order information. The existing analysis for algorithms using noise in the first-order information is quite involved and hides the es…
A new method for machine learning updates reduces complexity and improves robustness.
problem Stochastic gradient updates are inefficient and sensitive to feature scaling.
method Incremental Gauss-Newton Descent (IGND) reduces the need for matrix operations and improves robustness.
result IGND improves robustness to sensitivity scaling and can be competitive with common stochastic optimizers.
For the implicit systems of first order ordinary differential equations on the plane there is presented the complete local classification of generic singularities of family of its phase curves up to smooth orbital equivalence. Besides the well known singularities of generic vector fields on the plane and the singularit…
Stabilizes online learning by using weighted reservoir sampling.
problem Real-world deployment sensitivity to outliers causes low accuracy in final solutions.
method Weighted reservoir sampling to stabilize ensemble model without additional data passes.
result Risk of ensemble classifier is bounded with respect to the underlying online learning method's regret.
We consider first order expansions of convex penalized estimators in high-dimensional regression problems with random designs. Our setting includes linear regression and logistic regression as special cases. For a given penalty function h and the corresponding penalized estimator β^, we construct a quantity η,…
Efficient algorithm for contextual bandits with first-order guarantees.
problem Adapting to low noise in contextual bandits.
method Reduction to online regression with logarithmic loss.
result Optimal and efficient first-order guarantees for contextual bandits.