Monotonic Linear Interpolation property in neural networks persists despite non-convexity.
problem Understanding the geometric properties of neural network loss landscapes.
method Tools from differential geometry to analyze the monotonicity of neural network weights.
result Sufficient conditions for the Monotonic Linear Interpolation property under mean squared error.
The monotonic linear interpolation in deep networks often leads to plateaus, revealing biases in optimization.
problem Plateaus in the optimization landscape of deep networks during monotonic linear interpolation.
method Investigated monotonic linear interpolation on deep neural networks, focusing on biases in weights and biases.
result Interpolating weights and biases differently can lead to significant differences in loss and accuracy, revealing biases in optimization.
Monotone neural networks can approximate and interpolate functions efficiently.
problem Understanding the efficiency and expressiveness of monotone neural networks.
method Solving the monotone interpolation problem using depth-4 networks and comparing size bounds with arbitrary networks.
result Monotone neural networks can approximate and interpolate functions efficiently, but may require exponential size in high dimensions.
Loose bounds found for least-norm interpolant in over-parameterized settings.
problem Failures of model-dependent generalization bounds for least-norm interpolation.
method Analysis of generalization performance of least-norm linear regressor in over-parameterized regime.
result Generalization bounds for least-norm interpolant can be very loose, even when true excess risk goes to zero.
This work ensures stability in POD basis interpolation for pMOR in hyperelasticity.
problem Stability of POD basis interpolation on Grassmann manifolds for pMOR in hyperelasticity.
method Stability conditions derived from Grassmannian Exponential map and principal angles.
result Explicit stability conditions for practical pMOR applications and non-monotonic error behavior.
Optimizes hard-to-optimize metrics using adaptive surrogates.
problem Training models with black-box and hard-to-optimize metrics.
method Expresses metric as a function of surrogates, solves optimization problem over relaxed surrogate space.
result Approach performs on par with known methods and adds value when metric form is unknown.
Alignment of neural network representations is influenced by SNR and sample size.
problem Understanding how neural network representations align across different conditions.
method Controlled training of neural networks on perturbed datasets, analyzing alignment and generalization.
result Alignment varies monotonically with SNR but non-monotonically with sample size, with minimal alignment near the interpolation threshold.
Adding inequality constraints (e.g. boundedness, monotonicity, convexity) into Gaussian processes (GPs) can lead to more realistic stochastic emulators. Due to the truncated Gaussianity of the posterior, its distribution has to be approximated. In this work, we consider Monte Carlo (MC) and Markov Chain Monte Carlo (MC…
We analyze ridge interpolators in correlated factor regression models using RDT.
problem Performance analysis of ridge interpolators in correlated factor regression models.
method Utilizing Random Duality Theory (RDT), we obtain precise closed form characterizations of optimization problems.
result Ridge interpolators can smooth out the excess prediction risk and exhibit double-descent behavior.
In this paper we prove a new matrix Li-Yau-Hamilton estimate for Kähler-Ricci flow. The form of this new Li-Yau-Hamilton estimate is obtained by the interpolation consideration originated in \cite{Ch1}. This new inequality is shown to be connected with Perelman's entropy formula through a family of differential equalit…
Paper investigates optimal interpolation methods in linear regression.
problem Understanding when interpolating methods generalize well in linear regression.
method Investigates optimal response-linear interpolators using functions linear in the response variable.
result Provides a closed-form expression for the optimal interpolator and shows it can be derived as the limit of gradient descent.
This paper provides a practical method to extract caplet volatilities from quoted data.
problem Extracting caplet volatilities from quoted data is complex and not straightforward.
method The paper presents a constructive algorithm based on criteria and robust outlier detection. It includes direct interpolation, bootstrap methods, and global search methods.
result The paper introduces methods to extract caplet volatilities that are arbitrage-free and consistent with quoted data.
New insights into Nadaraya-Watson interpolators show varied generalization behaviors.
problem Understanding generalization of interpolating predictors, especially in noisy data.
method Revisiting Nadaraya-Watson estimator with a single hyperparameter.
result Multiple overfitting behaviors exist, ranging from catastrophic to tempered.
Study precise estimators for correlated data using RDT.
problem Analyzing estimators in correlated linear regression models.
method Utilized Random Duality Theory to characterize prediction risk.
result Precise closed form characterizations of estimators' risk.
It is widely believed that the prediction accuracy of decision tree models is invariant under any strictly monotone transformation of the individual predictor variables. However, this statement may be false when predicting new observations with values that were not seen in the training-set and are close to the location…
The paper studies optimal transport in linear quadratic systems and derives interpolation inequalities.
problem Optimal transport problem in Linear Quadratic optimal control systems.
method Well-posedness of the Monge problem, regularity of optimal transport map, displacement interpolation of measures.
result Derivation of general interpolation inequalities for entropy functionals.
Deep linear networks can closely approximate interpolants without improving risk.
problem Understanding the risk bounds of deep linear networks compared to minimum ℓ 2 \ell_2 ℓ 2 -norm solutions. method Bounding excess risk of interpolating deep linear networks trained using gradient flow.
result Deep linear networks can closely approximate or match minimum ℓ 2 \ell_2 ℓ 2 -norm solutions in terms of risk. We study the risk of minimum-norm interpolants of data in Reproducing Kernel Hilbert Spaces. Our upper bounds on the risk are of a multiple-descent shape for the various scalings of d = n α d = n^α d = n α , α ∈ ( 0 , 1 ) α\in(0,1) α ∈ ( 0 , 1 ) , for the input dimension d d d and sample size n n n . Empirical evidence supports our finding that minimum-norm interpo…
A new tradeoff between regularization and sharpness improves model performance in overparameterized settings.
problem Improving model performance in overparameterized settings with minimum-norm interpolators.
method Proposes a regularization-sharpness tradeoff for overparameterized linear regression with an ℓ^p penalty.
result Empirical validation shows the tradeoff terms can distinguish performant linear interpolators.
New bounds for linear interpolators show how they generalize under covariate shifts.
problem Understanding how linear interpolators generalize under covariate shifts.
method Proved non-asymptotic excess risk bounds for benignly-overfit linear interpolators in transfer learning.
result Identified beneficial and malignant covariate shifts based on overparameterization degree.
REPAIR mitigates variance collapse to enable linear interpolation between SGD solutions.
problem Linear interpolation between SGD solutions is difficult due to variance collapse in permuted activations.
method REPAIR rescales preactivations of interpolated networks to mitigate variance collapse.
result 60%-100% relative barrier reduction across various architectures and tasks.
The study tests inferences about neural network optimization from linear interpolation of loss landscapes.
problem Understanding the difficulty of neural network optimization problems.
method Linear interpolation of neural network loss landscapes, systematic evaluation of various factors.
result Linear interpolation does not correlate with model performance, challenging prior intuition.
Monotonic relationship found between in-distribution and out-of-distribution performance.
problem Understanding performance of machine learning models under distribution shifts.
method Analyzing ridge-regularized models and linear inverse problems under covariate shift.
result Monotonic relationship between in-distribution and out-of-distribution performance for certain models.
This paper analyzes error in SKI for Gaussian Processes, providing conditions for linear time inference.
problem Lack of rigorous theoretical error analysis for SKI.
method Proved error bounds for SKI Gram matrix, examined error effects, provided practical guidelines.
result Identified two dimensionality regimes for SKI's scalability-accuracy trade-offs.
A new image interpolation model using sparse representation and nonlocal linear regression.
problem Image interpolation without blurring and noise.
method Sparse representation, nonlocal self-similarity, nonlocal linear regression, adaptive sub-dictionary learning, weighted encoding.
result Our method outperforms state-of-the-art methods in quantitative measures and visual quality.
Study optimizes linear regression analysis for high-dimensional settings.
problem Understanding high-dimensional linear regression with interpolation and regularization.
method Localized uniform convergence analysis of optimistic rates for linear regression.
result Recover guarantees for ridge and LASSO regression under random designs.
Optimal machine learning requires interpolating training data in high-dimensional linear regression.
problem Achieving optimal predictive risk in overparameterized linear regression models.
method Analyzing proportional asymptotics of random design and label noise variance.
result Optimal performance in linear regression requires fitting training data to higher accuracy than inherent noise.
The paper bounds and identifies joint probabilities in causal inference with monotonicity assumptions.
problem Bounding and identifying joint probabilities of potential outcomes and observed variables under monotonicity assumptions.
method Proposes new families of monotonicity assumptions, formulates bounding problem as linear programming, introduces new monotonicity assumption for identification.
result Validated methods through numerical experiments and applied to real-world datasets.
We propose learning deep models that are monotonic with respect to a user-specified set of inputs by alternating layers of linear embeddings, ensembles of lattices, and calibrators (piecewise linear functions), with appropriate constraints for monotonicity, and jointly training the resulting network. We implement the l…
Efficiently computes quasiconcave envelope with limited data.
problem Approximating unknown quasiconcave function with partial information.
method Solves value problem and interpolation problem with polynomial and logarithmic LPs.
result Efficiently computes quasiconcave envelope with limited data.
Gradient flow in parameters equals linear interpolation in outputs.
problem Understanding and optimizing training algorithms in deep learning.
method Proving equivalence between gradient flow in parameter space and linear interpolation in output space, and deriving formulas for global minima.
result Gradient flow in parameters can be transformed into linear interpolation in outputs, leading to global minima.
The paper extends a variance gamma model to quadratic functions, reducing arbitrage and computational costs.
problem Creating an arbitrage-free interpolation for option pricing models.
method Generalizing the local variance gamma model to a piecewise quadratic local variance function.
result The quadratic model results in an arbitrage-free interpolation of class C3, reducing knots and computational cost.
Bagging stabilizes linear interpolators, improving their generalization performance.
problem Unstable linear interpolators fail on noisy data.
method Introduced multiplier-bootstrap-based bagged least square estimator.
result Bagging effectively mitigates variance, leading to bounded prediction risk.
In this paper, we establish a general monotonicity formula of the following elliptic system $$ Δu_i+f_i(u_1,...,u_m)=0 \quad {\rm in} Ω, \label{0.1} $$ where Ω ⊂ ⊂ R n Ω\subset\subset \mathbb{R}^n Ω ⊂⊂ R n is a bounded domain, ( f i ( u 1 , . . . , u m ) ) = ∇ F ( u ⃗ ) (f_i(u_1,...,u_m))=\nabla F(\vec{u}) ( f i ( u 1 , ... , u m )) = ∇ F ( u ) , and F ( u ⃗ ) F(\vec{u}) F ( u ) is a given smooth function of u ⃗ = ( u 1 , . . . , u m ) \vec{u}=(u_1,...,u_m) u = ( u 1 , ... , u m ) …
Lower bounds show OLS outperforms basis pursuit in overparameterized linear regression.
problem Excess risk of sparse interpolating procedures in overparameterized linear regression.
method Proved lower bounds on excess risk for OLS and basis pursuit.
result Excess risk of basis pursuit can converge at an exponentially slower rate than OLS.
New algorithm maximizes non-monotone adaptive submodular functions in linear time.
problem Maximizing non-monotone adaptive submodular functions subject to a cardinality constraint.
method Developed a linear-time algorithm for non-monotone adaptive submodular maximization.
result Achieved a 1 / e − ε 1/e-ε 1/ e − ε approximation ratio with O ( n ε − 2 log ε − 1 ) O(nε^{-2}\log ε^{-1}) O ( n ε − 2 log ε − 1 ) value oracle queries. Study finds exact limits for sparse regression with fewer observations than usual.
problem Understanding sparse linear regression with sublinear sparsity.
method Adaptive interpolation method and modified AMP algorithm.
result Exact asymptotic expressions for mutual information and MMSE in sublinear sparsity.
The null energy condition is characterized via convexity of entropy in Lorentzian manifolds.
problem Characterizing the null energy condition in Lorentzian manifolds.
method Characterization via convexity of the relative entropy along displacement interpolations on null hypersurfaces.
result The null energy condition is characterized in terms of convexity of the relative entropy.
Graphons connect graph structures to manifold properties.
problem Interpolating between graphs and manifolds.
method Graph-to-graphon and graphon-to-manifold convergence.
result Established monotonicity inequality linking combinatorial and geometric parameters.
New model leads to optimal test loss in sparse linear regression.
problem Sparse linear regression with low test loss despite interpolating training data.
method Developed a new parametrization of the model that combines benefits of ℓ1 and ℓ2 norms.
result Training via gradient descent leads to an interpolator with near-optimal test loss.
Interpolation hurts robust generalization even without noise.
problem The challenge of robust generalization in the absence of noise.
method Avoiding interpolation through ridge regularization.
result Ridge regularization improves robust generalization.
A continuing mystery in understanding the empirical success of deep neural networks is their ability to achieve zero training error and generalize well, even when the training data is noisy and there are more parameters than data points. We investigate this overparameterized regime in linear regression, where all solut…
SKI accelerates GP inference with sparse grids to handle higher dimensions.
problem SKI scales poorly in high dimensions due to dense grid size.
method Sparse grids within SKI framework, novel matrix-vector multiplication algorithm.
result SKI can be scaled to higher dimensions while maintaining accuracy.
Grokking occurs in simple binary logistic classification near linear separability and noise.
problem Delayed generalization in binary logistic classification.
method Analytical and empirical insights into gradient descent dynamics near critical points.
result Logistic regression exhibits grokking when training data is nearly linearly separable from the origin with strong noise.
This paper analyzes the interpolation error of nonlinear Attention compared to linear regression.
problem Understanding the interpolation error of nonlinear Attention in high-dimensional settings.
method Derives explicit expressions for mean-squared interpolation error using signal-plus-noise model and random matrix theory.
result Nonlinear Attention generally incurs a larger interpolation error than linear regression, but this gap can be reversed with structured signals.
Adversarial training improves linear regression solutions, revealing sparsity and abrupt interpolation.
problem Adversarial attacks on linear regression models.
method Formulated as a convex problem, adversarial training is used to find robust solutions that are sparse and interpolate data.
result Adversarial training with small disturbances gives the solution with the minimum-norm that interpolates the training data, revealing abrupt transition into interpolation.
Noise affects the effectiveness of interpolating models, especially those with strong inductive biases.
problem The impact of noise on interpolating models with strong inductive biases.
method Analyzing linear and classification models with sparse ground truths, proving fast rates for interpolators.
result Strong inductive biases can lead to faster but noisier interpolators, contrary to intuition.
Efficient algorithms find optimal monotone transforms for calibration under strictly convex losses.
problem Calibrating estimations to improve performance with monotone transforms.
method Proposed linear-time and space algorithm for finding optimal monotone transforms for specific loss functions. Also proposed an anytime algorithm with linear space and pseudo-linearithmic time complexity.
result Optimal monotone transforms are unique and can be found efficiently for various strictly convex loss functions.