MaxEnt Model Correction improves reinforcement learning model accuracy.
problem Improving reinforcement learning model accuracy and convergence.
method MaxEnt Model Correction (MoCo) procedure to correct model's next-state distributions.
result MoCoVI and MoCoDyna algorithms converge faster and effectively use approximate models.
In this note, we derive the characteristic function expansion for logarithm of the underlying asset price in corrected Heston model as proposed by Fouque and Lorig.
Procedure confirms covariate balance anytime from unlabeled data.
problem Ensuring covariate balance in sequential data.
method Time-uniform confidence sequences for continuous monitoring.
result Probability of false confirmation controlled.
Survey on learning Boolean functions in computational theory.
problem Learning Boolean function classes in computational theory.
method Overview of known results in PAC and related models.
result Discussion of various learning results for Boolean functions.
Algorithm corrects mistakes in imitation learning tasks.
problem Covariate shift problem in learning from demonstrations.
method Value Iteration with Negative Sampling (VINS) for conservative extrapolation.
result VINS corrects mistakes of the behavioral cloning policy.
Paper proves autodiff systems are correct for non-differentiable functions.
problem Correctness of autodiff systems for non-differentiable functions in deep learning.
method Investigation of PAP functions and introduction of intensional derivatives.
result Intensional derivatives always exist and coincide with standard derivatives for almost all inputs.
The paper examines when importance weighting is needed for nonparametric and misspecified models.
problem When is importance weighting correction needed for covariate shift adaptation?
method Analysis of IW-corrected kernel ridge regression in various settings.
result The importance weighting correction is needed for nonparametric and misspecified models to obtain the best approximation of the true unknown function.
This paper corrects the proof of the Theorem 2 from the Gower's paper \cite[page 5]{Gower:1982} as well as corrects the Theorem 7 from Gower's paper \cite{Gower:1986}. The first correction is needed in order to establish the existence of the kernel function used commonly in the kernel trick e.g. for k-means clusterin…
New method corrects bias in datasets using cumulative distribution functions.
problem Varying domains and biased datasets lead to differences between training and target distributions.
method Empirical cumulative distribution function estimates of the target distribution, rigorously generalized.
result Method is more robust, not reliant on parameter tuning, and performs similarly to state-of-the-art techniques.
Noise-corrected Langevin algorithm improves sampling from noisy data.
problem Sampling from noisy data with biased score function.
method Noise-corrected Langevin algorithm using noisy score function.
result Bias due to noisy data is removed, improving sampling accuracy.
Expectation Propagation (EP) provides a framework for approximate inference. When the model under consideration is over a latent Gaussian field, with the approximation being Gaussian, we show how these approximations can systematically be corrected. A perturbative expansion is made of the exact but intractable correcti…
SCoreBO improves Bayesian optimization by learning hyperparameters and self-correcting.
problem Efficient hyperparameter tuning for Gaussian process models in Bayesian optimization.
method Introduces SAL and SCoreBO, which prioritize hyperparameter learning and perform simultaneous optimization and learning.
result SCoreBO outperforms state-of-the-art methods on traditional benchmarks and atypical tasks.
Framework uses neural networks to learn fitness functions for machine programming.
problem Automatic software generation and crafting effective fitness functions.
method Genetic algorithms augmented with neural networks and a search heuristic.
result Framework discovers more correct programs with fewer candidate generations.
Paper analyzes convergence of PAM method for low-rank factorization models.
problem Convergence analysis of PAM method with subspace correction for low-rank factorization models.
method Majorized proximal alternating minimization (PAM) method with subspace correction.
result Established full convergence of PAM method under KL property and column ℓ2,0-norm condition. Corrected a false lemma in Cimasoni's work on linking theory.
problem A false lemma in Cimasoni's geometric construction of the Conway potential function.
method Presented counterexamples and a detailed proof of the corrected lemma.
result The lemma is false and its correction has significant consequences for subsequent works.
New method for estimating treatment effects without complex propensity models.
problem Estimating treatment effects in dynamic treatment regimes.
method Recursive Riesz representer estimation for de-biasing corrections.
result Directly estimates de-biasing corrections without auxiliary models.
This paper improves deep learning model consistency through ensemble methods.
problem Consistency and correct-consistency issues in deep learning models.
method Formal definition of consistency and correct-consistency, proving ensemble improvement, proposing dynamic snapshot ensemble method.
result Ensemble methods can improve correct-consistency of deep learning models.
Paper stabilizes generative model training with synthetic data.
problem Self-consuming loops in generative model training.
method Introducing an idealized correction function and self-correction functions.
result Self-consuming loops can be exponentially more stable with the right correction.
In deep neural network, the cross-entropy loss function is commonly used for classification. Minimizing cross-entropy is equivalent to maximizing likelihood under assumptions of uniform feature and class distributions. It belongs to generative training criteria which does not directly discriminate correct class from co…
Resampling outperforms reweighting for correcting biased data in machine learning models.
problem Correcting sampling bias in machine learning models trained on biased data sets.
method Compared resampling and reweighting techniques, focusing on their performance with stochastic gradient algorithms.
result Resampling outperforms reweighting when combined with stochastic gradient algorithms.
Derives log-corrections in AdS4/CFT3 using supergravity localization.
problem Factorizing log-corrections in AdS4/CFT3.
method Supergravity localization, Atiyah-Singer index theorem, fixed points (NUTs), fixed two-manifolds (Bolts).
result General fixed-point formula for log-corrections in large N expansion.
Study loop corrections in random feature models affecting training and test errors.
problem Analyzing loop corrections in random feature models to understand training and test errors.
method Statistical physics and effective field theory approach to study loop corrections.
result Derived loop corrections to training error, test error, and generalization gap.
This paper is concerned with the following Markovian stochastic differential equation of mean-reversion type \[ dR_t= (θ+σα(R_t, t))R_t dt +σR_t dB_t \] with an initial value R0=r0∈R, where θ∈R and σ>0 are constants, and the mean correction function $α:\mathbb{R}\times[0,\infty)\to α(x,t)\…
New method improves sampling from score-based models by correcting bias.
problem Bias in sampling from score-based diffusion models.
method Metropolis-Hastings or Barker's accept-reject steps to correct bias, using the score function.
result Improves sample quality on synthetic and image datasets, yielding consistent gains in FID.
This paper quantifies how well random neural networks can approximate continuous functions.
problem Approximating continuous functions with random neural networks.
method Investigates three types of random neural networks: infinite width, subsampled, and corrected. Analyzes approximation rates and provides bounds.
result A function can be approximated with complexity proportional to δ and d. In the context of machine learning, disparate impact refers to a form of systematic discrimination whereby the output distribution of a model depends on the value of a sensitive attribute (e.g., race or gender). In this paper, we propose an information-theoretic framework to analyze the disparate impact of a binary cla…
We propose an approach for approximating the partition function which is based on two steps: (1) computing the partition function of a simplified model which is obtained by deleting model edges, and (2) rectifying the result by applying an edge-by-edge correction. The approach leads to an intuitive framework in which o…
A corrective neural network approach improves memorization and learning efficiency.
problem Improving neural network memorization and learning efficiency.
method Divide neural network into groups to sequentially approximate and correct errors.
result Two-layer neural networks can memorize arbitrary labels with optimal number of ReLUs.
We correct for sampling bias in training models to improve real-world performance.
problem Sampling bias causes discrepancies between lab and real-world model performance.
method Bayesian risk minimization and derived bias-corrected loss functions.
result Our approach integrates seamlessly into current learning paradigms and improves model performance.
We propose and analyze an alternate approach to off-policy multi-step temporal difference learning, in which off-policy returns are corrected with the current Q-function in terms of rewards, rather than with the target policy in terms of transition probabilities. We prove that such approximate corrections are sufficien…
DisCor corrects reinforcement learning issues by re-weighting collected data.
problem Reinforcement learning algorithms struggle with instability and sensitivity to hyperparameters.
method DisCor reweights collected data to mitigate issues caused by the distribution of experience.
result DisCor improves reinforcement learning in challenging settings like multi-task learning and noisy reward signals.
Improves sampling quality in model composition using MH-like acceptance rule for score-based diffusion models.
problem Inability to apply MH corrections in score-based diffusion models for model composition.
method Introduces a novel MH-like acceptance rule based on line integration of the score function.
result Relative improvements similar to energy-based models without explicit energy parameterization.
This research improves online learning by correcting for target shift in machine learning.
problem Online learning struggles with distributional shift, especially in target values.
method Derives closed-form expressions for online and offline learning, and target correction.
result Online kernel-based learning can learn the same predictor as offline learning with target correction.
A corrected EI acquisition function handles noisy observations in Bayesian optimization.
problem Noisy observations in Bayesian optimization.
method Proposes a modified expected improvement (EI) acquisition function that incorporates covariance information from the Gaussian Process model.
result Achieves a sublinear convergence rate on cumulative regret bound under heteroscedastic observation noise.
Mitigates overfitting in UU classification from two unlabeled datasets.
problem Overfitting in the UU classification method.
method Wrapping negative empirical risk terms with correction functions and proving consistency.
result Successfully mitigates overfitting and improves classification accuracy.
Corrects pseudo log-likelihood method issues in various applications.
problem Log-likelihood function unbounded issues in pseudo log-likelihood methods.
method Provided a counterexample and corrected algorithms in previous literature.
result Ensured well-definedness of maximum pseudo log-likelihood estimation.
Given an element in the first homology of a rational homology 3-sphere Y, one can consider the minimal rational genus of all knots in this homology class. This defines a function Θ on H1(Y;Z), which was introduced by Turaev as an analogue of Thurston norm. We will give a lower bound for this function usi…
New IRL algorithm for continuous state spaces with formal guarantees.
problem Finding a reward function for expert behavior in continuous state spaces.
method Modeling the system using orthonormal functions and providing correctness proofs.
result Proof of correctness and formal guarantees on sample and time complexity.
The article shows how to count small eigenvalues without assuming Morse functions.
problem Counting small eigenvalues without assuming Morse functions.
method Using the Witten Laplacian and persistent cohomology.
result The rescaled logarithms of small eigenvalues are determined by bar code lengths.
This paper explains how deep learning performs hierarchical learning efficiently.
problem How deep learning can perform hierarchical learning efficiently.
method Backward feature correction principle and SGD training.
result Deep learning can efficiently train complex hierarchical tasks using SGD.
Corrected Monti's blow-up analysis for H-minimizing sets in Heisenberg group.
problem Blow-up analysis of H-minimizing sets in Heisenberg group with corrected partial differential equation.
method Revised Monti's results on blow-ups of H-perimeter minimizing sets in Hn and corrected the partial differential equation for the limit function. result Corrected the partial differential equation for the limit function of blow-ups in Heisenberg group.
String geometry theory uniquely determines classical action with T-symmetry.
problem Non-renormalizability and loop corrections in string theory.
method Distinguishes effects of β and ħ parameters, proving no loop corrections.
result No loop corrections in string geometry theory, avoiding non-renormalizability.
Bayesian priors offer a compact yet general means of incorporating domain knowledge into many learning tasks. The correctness of the Bayesian analysis and inference, however, largely depends on accuracy and correctness of these priors. PAC-Bayesian methods overcome this problem by providing bounds that hold regardless …
Learning robot objective functions from human input has become increasingly important, but state-of-the-art techniques assume that the human's desired objective lies within the robot's hypothesis space. When this is not true, even methods that keep track of uncertainty over the objective fail because they reason about …
We address the problem of learning vector representations for entities and relations in Knowledge Graphs (KGs) for Knowledge Base Completion (KBC). This problem has received significant attention in the past few years and multiple methods have been proposed. Most of the existing methods in the literature use a predefin…
SLOE speeds up logistic regression in high dimensions with accurate signal strength estimation.
problem Poor performance of logistic regression in high-dimensional settings.
method SLOE reparameterizes the signal strength for faster and more accurate estimation.
result SLOE provides a fast and accurate method for dimensionality correction in logistic regression.
A 'holographic formula' expressing the functional determinant of the scattering operator in an asymptotically locally anti-de Sitter(ALAdS) space has been proposed in terms of a relative functional determinant of the scalar Laplacian in the bulk. It stems from considerations in AdS/CFT correspondence of a quantum corre…
Corrects an error in isospectral lens spaces formula for composite q.
problem Isospectral lens spaces on forms but not on functions for composite q.
method Detailed calculations and reworking of formulas for composite q.
result Formulas (3) and (4) in previous work must be revised for composite q.