New PAC-Bayes method updates priors without losing confidence information.
problem Lack of sequential prior updates in PAC-Bayes without losing confidence information.
method Recursive PAC-Bayes decomposition of expected loss.
result Sequential prior updates with no information loss.
Study achieves fairness without demographic info, improving regression tasks.
problem Achieve fairness in models without prior demographic info.
method VFair method to minimize training loss variance, dynamic update approach.
result Regression tasks can achieve significant fairness improvement without prior demographics.
Optimal sensor placement minimizes information loss from simulations.
problem Designing efficient sensor networks for spatiotemporal processes.
method Model-based sensor placement criterion with sparse variational inference and Gauss-Markov priors.
result Our method identifies sensor networks that minimize information loss from simulated data.
Prior design is one of the most important problems in both statistics and machine learning. The cross validation (CV) and the widely applicable information criterion (WAIC) are predictive measures of the Bayesian estimation, however, it has been difficult to apply them to find the optimal prior because their mathematic…
Paper tackles class-incremental learning by combining self-supervised learning to mitigate prior information loss.
problem Catastrophic forgetting and prior information loss in class-incremental learning.
method Combining self-supervised learning with class-incremental learning to mitigate prior information loss.
result Proposed method outperforms state-of-the-art methods.
Forecastability measures predictive information across horizons.
problem How much predictive information is available at each prediction horizon?
method Develops the consequences of mutual information between future observations and information set.
result Forecastability is a profile reflecting process dependence structure, with properties like compression and truncation error.
Physics-informed kernel learning integrates physical priors into machine learning models.
problem Tackles the integration of physical laws into machine learning models for improved accuracy and efficiency.
method Uses Fourier methods to approximate the kernel and minimizes a physics-informed risk function.
result Demonstrates PIKL outperforms physics-informed neural networks and traditional PDE solvers in various scenarios.
In this work, we address the problem of modifying textual attributes of sentences. Given an input sentence and a set of attribute labels, we attempt to generate sentences that are compatible with the conditioning information. To ensure that the model generates content compatible sentences, we introduce a reconstruction…
Regularization methods, specifically those which directly alter weights like L1 and L2, are an integral part of many learning algorithms. Both the regularizers mentioned above are formulated by assuming certain priors in the parameter space and these assumptions, in some cases, induce sparsity in the parameter sp…
A new method optimizes anomaly scoring from score distribution to improve AD performance.
problem Vulnerability to anomaly contamination and lack of adaptability in existing AD methods.
method Optimizes anomaly scoring function from score distribution perspective, using Overlap loss.
result Overlap loss-based AD models significantly outperform state-of-the-art methods.
The paper introduces a method to incorporate expert opinion on observable quantities into statistical models.
problem Tackling the challenge of integrating expert knowledge on observable quantities into statistical models.
method The approach involves updating a prior belief using a loss function that reflects expert opinion on observable quantities.
result The method allows for a flexible specification of expert opinion and is straightforward to implement.
Study on optimal information acquisition in Kyle model with entropy cost.
problem Optimal information acquisition in Kyle model with entropy cost.
method Continuous signals are optimal, and any signal with a logit posterior distribution yields the same ex-ante value.
result Posterior expected payoff becomes normally distributed as information acquisition cost increases.
The performance of the state-of-the-art image segmentation methods heavily relies on the high-quality annotations, which are not easily affordable, particularly for medical data. To alleviate this limitation, in this study, we propose a weakly supervised image segmentation method based on a deep geodesic prior. We hypo…
New methods evaluate data representations by complexity of low-loss predictor learning.
problem Evaluating quality of data representations for downstream tasks.
method Surplus Description Length (SDL) and ε Sample Complexity (εSC) methods.
result Methods measure the information needed to approximate optimal predictor up to specified tolerance.
PD-PINNs accelerate PINN training by incorporating task-specific dictionaries.
problem Training PINNs is slow and lacks theoretical error bounds.
method Integrates task-dependent dictionaries into PINNs to enhance convergence.
result PD-PINNs achieve faster convergence and bounded prediction errors.
Estimates optimal transport maps with known cost functions.
problem Ensuring optimal transport maps correspond to real-world usefulness.
method Differentiable neural ground costs with known Monge map forms.
result General approach for incorporating prior information.
Semi-supervised clustering aims to introduce prior knowledge in the decision process of a clustering algorithm. In this paper, we propose a novel semi-supervised clustering algorithm based on the information-maximization principle. The proposed method is an extension of a previous unsupervised information-maximization …
VAEs improve generalization by regulating mutual information, contrary to intuition.
problem Improving generalization in VAEs.
method Rate-distortion analyses controlling rate strength, network capacity, and generalization difficulty.
result Decreasing the strength of the rate paradoxically improves generalization.
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…
Bayesian neural networks incorporate domain knowledge through variational inference.
problem Specifying priors for Bayesian neural networks that capture domain knowledge is challenging.
method Proposes a framework for integrating domain knowledge into BNN priors through variational inference.
result BNNs with proposed domain knowledge priors outperform those with standard priors, achieving better predictive performance.
We present a powerful new loss function and training scheme for learning binary hash codes with any differentiable model and similarity function. Our loss function improves over prior methods by using log likelihood loss on top of an accurate approximation for the probability that two inputs fall within a Hamming dista…
The cross-entropy loss commonly used in deep learning is closely related to the defining properties of optimal representations, but does not enforce some of the key properties. We show that this can be solved by adding a regularization term, which is in turn related to injecting multiplicative noise in the activations …
A new framework improves tensor completion accuracy by considering numerical priors.
problem Tensor completion accuracy loss due to ignoring numerical priors.
method Generalized CP Decomposition Tensor Completion (GCDTC) framework incorporating numerical priors.
result GCDTC framework outperforms state-of-the-arts in non-negative tensor completion.
This paper presents a novel clustering concept that is based on jointly learned nonlinear transforms (NTs) with priors on the information loss and the discrimination. We introduce a clustering principle that is based on evaluation of a parametric min-max measure for the discriminative prior. The decomposition of the pr…
P-BO reduces black-box adversarial attacks by 10x with Bayesian optimization and function prior.
problem Efficiently generating adversarial examples against black-box models.
method Prior-guided Bayesian Optimization (P-BO) with a function prior initialized from a surrogate model.
result Significantly reduces the number of queries needed for adversarial attacks.
Proposes VCLANC for attributed network clustering using node and attribute embeddings.
problem Lack of mutual affinity exploitation between nodes and attributes in graph convolution.
method Dual variational auto-encoders for node and attribute embeddings, Gaussian mixture model priors, mutual distance and clustering assignment hardening losses.
result Demonstrates effectiveness on real-world attributed network datasets.
New approach uses autoregressive models to explore and quantify uncertainty in decision-making.
problem Quantifying and exploring uncertainty in online decision-making.
method Reformulates uncertainty as missing future outcomes, training autoregressive models for next-outcome prediction.
result Establishes a reduction from online learning to offline next-outcome prediction, controlling Bayesian regret by sequence prediction loss.
Unified framework simplifies DPO algorithms for LLM alignment.
problem Vast number of DPO variants complicates model alignment.
method Mutual information inspired unifying framework with flexible priors.
result Many DPO variants can be derived from the new framework.
New unsupervised image translation method detects changes without labeled data.
problem Detecting changes in images without labeled data.
method Affinity-based change priors and weighted loss functions trained on convolutional neural networks.
result Proposed method outperforms state-of-the-art algorithms in detecting changes.
We propose a physics-informed Echo State Network (ESN) to predict the evolution of chaotic systems. Compared to conventional ESNs, the physics-informed ESNs are trained to solve supervised learning tasks while ensuring that their predictions do not violate physical laws. This is achieved by introducing an additional lo…
Proposes mutual information for regression without prior knowledge.
problem Regression tasks without prior model knowledge.
method Mutual information learning formulation, SGD convergence analysis.
result High dimensionality can be beneficial with a threshold.
This work interprets SFA through variational inference, relaxing linearity constraints.
problem Recover non-linear SFA from variational inference.
method Probabilistic interpretation of SFA through variational inference, relaxing linearity constraints.
result Reinterprets SFA as a variational framework, allowing slowness as a regularizer to reconstruction loss.
DPlis improves privacy in deep learning models by smoothing loss functions.
problem Privacy leakage in deep learning models trained on private data and low model performance.
method DPlis constructs a smooth loss function to favor noise-resilient models.
result DPlis effectively boosts model quality and training stability under privacy constraints.
Improves AI-prior reliability for Bayesian inference.
problem Error propagation from predictive models into posterior inference.
method Rectified AI-informed prior elicitation framework.
result Significant reduction in bias and improvement in predictive performance.
We develop a new theoretical framework, the \emph{envelope complexity}, to analyze the minimax regret with logarithmic loss functions and derive a Bayesian predictor that adaptively achieves the minimax regret over high-dimensional ℓ1-balls within a factor of two. The prior is newly derived for achieving the mini…
Survey on optimizing topological descriptors for machine learning.
problem Optimizing topological priors in machine learning models.
method Minimizing topologically-informed losses using gradient descent.
result Various techniques enable optimization of persistence-based loss functions.
A new method improves uncertainty quantification in Bayesian inference.
problem Poor uncertainty quantification in traditional Gibbs posteriors.
method Sequential Gibbs posteriors with a Bernstein-von Mises theorem.
result Sequential Gibbs posteriors provide better frequentist coverage.
A new method estimates the learning coefficient using empirical loss.
problem Estimating the learning coefficient in complex models.
method Numerical estimation using Empirical Loss.
result Our method outperforms existing techniques in terms of bias and variance.
Variational Auto-encoders (VAEs) have been very successful as methods for forming compressed latent representations of complex, often high-dimensional, data. In this paper, we derive an alternative variational lower bound from the one common in VAEs, which aims to minimize aggregate information loss. Using our lower bo…
Hi-fi priors enhance BNNs by learning flexible activations.
problem Challenging to impose function-space priors on BNNs.
method Optimization techniques to learn flexible activations.
result BNNs with flexible activations can achieve desired priors.
New method integrates topological knowledge into data embeddings.
problem Lack of general tools to incorporate prior topological knowledge into embeddings.
method Introduces new topological losses to topologically regularize data embeddings.
result Natural representation of simple models like clusters and flares.
Bayesian nonparametric framework improves robustness of MI estimation.
problem Challenges in exact MI computation in high dimensions with intractable likelihoods.
method Uses a Dirichlet process posterior to regularize MI loss, reducing sensitivity to fluctuations and outliers.
result Significant improvements in convergence over EDF-based methods, enhancing robustness and accuracy.
New research shows posterior collapse in VAEs isn't just about KL-divergence.
problem Posterior collapse in Variational Autoencoders (VAEs).
method Analyzes the loss surface of deep autoencoder networks and proves the existence of bad local minima.
result Posterior collapse in VAEs is caused by bad local minima, not just KL-divergence.
Common statistical practice has shown that the full power of Bayesian methods is not realized until hierarchical priors are used, as these allow for greater "robustness" and the ability to "share statistical strength." Yet it is an ongoing challenge to provide a learning-theoretically sound formalism of such notions th…
A new algorithm learns causal relationships from multimodal data.
problem Discovering causal relationships in exploratory settings without prior information.
method causalPIMA algorithm using multimodal data and physics constraints.
result Learned causal structure and key features in fully unsupervised settings.
New method improves Robbins-Monro algorithm convergence with prior information.
problem Improving convergence speed of Robbins-Monro algorithm.
method Integrates prior information into Robbins-Monro iteration without regression model.
result Prior-information Robbins-Monro sequence converges faster than standard.
We propose an online convex optimization algorithm (RescaledExp) that achieves optimal regret in the unconstrained setting without prior knowledge of any bounds on the loss functions. We prove a lower bound showing an exponential separation between the regret of existing algorithms that require a known bound on the los…
A novel minimax classifier tackles imbalanced datasets with few minority samples.
problem Imbalanced datasets with limited minority samples.
method Proposes a novel minimax learning algorithm with two steps: minimization and maximization.
result The algorithm improves model performance compared to existing methods.