AI recovers lost art from x-rays.
problem Reconstructing lost artwork under layers of x-ray imaging.
method Neural style transfer applied to x-radiographs.
result Reconstructed lost artwork visible through x-rays.
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
168,786 papers · 148 categories
Trend · papers per month
48 results for “lost art”
A prediscretisation of numerical attributes which is required by some rule learning algorithms is a source of inefficiencies. This paper describes new rule tuning steps that aim to recover lost information in the discretisation and new pruning techniques that may further reduce the size of rule models and improve their…
Single model corrects JPEG artifacts for various compression settings.
problem JPEG compression artifacts due to aggressive quantization.
method Parameterized architecture using quantization matrix.
result State-of-the-art performance across different quality settings.
Conformally equivariant quantization is a peculiar map between symbols of real weight and differential operators acting on tensor densities, whose real weights are designed by and . The existence and uniqueness of such a map has been proved by Duval, Lecomte and Ovsienko for a generic weight . Later, Si…
A variety of graph neural networks (GNNs) frameworks for representation learning on graphs have been recently developed. These frameworks rely on aggregation and iteration scheme to learn the representation of nodes. However, information between nodes is inevitably lost in the scheme during learning. In order to reduce…
The area of Handwritten Signature Verification has been broadly researched in the last decades, but remains an open research problem. In offline (static) signature verification, the dynamic information of the signature writing process is lost, and it is difficult to design good feature extractors that can distinguish g…
In unsupervised learning, there is no apparent straightforward cost function that can capture the significant factors of variations and similarities. Since natural systems have smooth dynamics, an opportunity is lost if an unsupervised objective function remains static during the training process. The absence of concre…
A graph model improves short text classification by integrating sentence relationships.
problem Sparse features in short text classification due to limited text length.
method PathWalk model combining graph networks and short sentences.
result PathWalk achieves state-of-the-art results on four datasets.
Study on inventory control with changing demand, proposing adaptive algorithms.
problem Inventory control with non-stationary demand distributions.
method Adaptive online algorithms optimizing base-stock policies.
result Sharp separation in adaptability across different inventory models.
The paper examines how macroeconomic control tools lost effectiveness, leading to a 'dark ages' period.
problem Loss of effectiveness of control tools in macroeconomic stabilization policy.
method Historical analysis of macroeconomic stabilization policy from 1948 to 1993.
result The overstatement of the Lucas critique and Kydland and Prescott's time-inconsistency led to a period of ineffective stabilization policy.
An Adjoint-Sensitivity Framework for Lost-in-the-Middle Phenomena in Causal Residual Transformersstat.ML
Framework calculates positional influence in causal residual Transformers.
problem Understanding positional influence in causal residual Transformers.
method Adjoint-sensitivity framework for positional influence in causal residual Transformers.
result Exact evolution of adjoint-energy influence density and decomposition into residual transmission, nonlocal Volterra, and local channels.
New method separates graph structure from node attributes to recover lost signal.
problem Standard representation learning on attributed graphs merges incompatible metric spaces, leading to geometrically flawed alignment.
method Custom variational autoencoder that separates manifold learning from structural alignment.
result Transforms geometric conflict into interpretable structural descriptor, uncovering connectivity patterns and anomalies.
Paper introduces adversarial lossy compression for video artifacts reduction.
problem Unpleasant reconstruction artifacts in standard video coding schemes at low bit-rates.
method Adversarial lossy video compression model minimizing an adversarial distortion objective.
result Reduction of perceptual artifacts and detail reconstruction under extreme compression.
Although the popular MNIST dataset [LeCun et al., 1994] is derived from the NIST database [Grother and Hanaoka, 1995], the precise processing steps for this derivation have been lost to time. We propose a reconstruction that is accurate enough to serve as a replacement for the MNIST dataset, with insignificant changes …
We consider the problem of training a model under the presence of label noise. Current approaches identify samples with potentially incorrect labels and reduce their influence on the learning process by either assigning lower weights to them or completely removing them from the training set. In the first case the model…
OmniMatch algorithm perfectly matches graphs without edge correlation.
problem Graph matching in the absence of edge correlation.
method OmniMatch algorithm for seeded multiple graph matching.
result OmniMatch aligns unseeded vertices across multiple networks efficiently and perfectly.
Gurau argued in [arXiv:1006.0714] that the gluing spaces arising as Feynman diagrams of three-dimensional group field theory are not all pseudo-manifolds. I dispute this conclusion: albeit not properly triangulated, these spaces are genuine pseudo-manifolds, viz. their singular locus is of codimension at least two.
Recurrent Neural Networks (RNN) can be difficult to deploy on resource constrained devices due to their size.As a result, there is a need for compression techniques that can significantly compress RNNs without negatively impacting task accuracy. This paper introduces a method to compress RNNs for resource constrained e…
A new method for clustering incomplete data.
problem Handling missing data in clustering.
method Bayes alignment for imputation and leachable component clustering.
result The proposed method outperforms state-of-the-art algorithms.
The vanishing ideal is a set of polynomials that takes zero value on the given data points. Originally proposed in computer algebra, the vanishing ideal has been recently exploited for extracting the nonlinear structures of data in many applications. To avoid overfitting to noisy data, the polynomials are often designe…
Two retraining techniques outperform fine-tuning in neural network pruning.
problem Improving accuracy and compression in neural network pruning.
method Weight rewinding and learning rate rewinding compared to fine-tuning.
result Rewinding techniques outperform fine-tuning in accuracy and compression.
Study suggests variable selection may not significantly reduce power in multivariate tests.
problem The feasibility of parsimonious variable selection in Hotelling's T2-test.
method Investigation of power loss when selecting small subsets of variables from multivariate data.
result Some evidence suggests no significant power loss over a wide range of alternatives.
How Unlucky is 25-Sigma?q-fin.GN
One of the more memorable moments of last summer's credit crunch came when the CFO of Goldman Sachs, David Viniar, announced in August that Goldman's flagship GEO hedge fund had lost 27% of its value since the start of the year. As Mr. Viniar explained, "We were seeing things that were 25-standard deviation moves, seve…
We study controlled systems which are uniformly observable and differentially observable with an order larger than the system state dimension. We establish that they may be transformed into a (partial) triangular canonical form but with possibly non locally Lipschitz functions. We characterize the points where this Lip…
Proposes a tensor Laplacian-based method for better subspace clustering of non-uniformly distributed data.
problem LRR's inability to handle non-uniform data distribution and local information loss.
method Tensor Laplacian Regularized Low-Rank Representation (TLRR) using hypergraph model and tensor Laplacian algorithm.
result Higher accuracy and precision in subspace clustering compared to state-of-the-art methods.
Deep learning has the potential to revolutionize quantum chemistry as it is ideally suited to learn representations for structured data and speed up the exploration of chemical space. While convolutional neural networks have proven to be the first choice for images, audio and video data, the atoms in molecules are not …
Scalable NAS by factorizing operators into subspaces.
problem Scaling up NAS search space while avoiding operator competition.
method Factorizing a large set of candidate operators into smaller subspaces.
result Achieved state-of-the-art performance on CIFAR10 and ImageNet.
A new variational method improves deep neural network inference.
problem Overparametrized deep neural networks struggle with variational approximations.
method A novel variational family with two independent linear subspaces.
result State-of-the-art performance across various tasks and datasets.
The paper examines domain generalization algorithms and finds empirical risk minimization performs well.
problem Comparing domain generalization algorithms is difficult due to inconsistent experimental conditions.
method Implemented DomainBed, a testbed for domain generalization with seven datasets and model selection criteria.
result Empirical risk minimization shows state-of-the-art performance across all datasets.
Nonholonomic Newmark methodmath.NA
Generalizes Newmark methods for nonholonomic systems.
problem Energy behavior in nonholonomic systems.
method Nonholonomic exponential map to generalize Newmark methods.
result Composition of two Newmark methods can improve energy behavior.
MCFNet recovers spatial detail and fuses it with semantic information for real-time segmentation.
problem Recovering spatial detail information and fusing it with semantic information in real-time.
method Proposes a new architecture (MCFNet) with feature refinement and fusion modules, and a gating unit.
result Achieves competitive performance with high speed (75.5% mIOU, 151.3 FPS on Cityscapes).
The article proposes optimal learning strategies for machine learning-based reliability analysis.
problem Improving computational efficiency and accuracy in machine learning-based reliability analysis.
method Theorems and mathematical proofs for optimal learning strategies considering and neglecting correlations among design samples.
result The optimal learning strategy considering Kriging correlation outperforms other methods in terms of reduced evaluations of performance functions.
Scalable Gaussian processes with latent Kronecker structure for large datasets.
problem Limited scalability of Gaussian processes for large datasets.
method Leveraging latent Kronecker structure, projecting kernel matrix onto latent Kronecker product, using iterative linear system solvers and pathwise conditioning.
result Outperforms state-of-the-art sparse and variational GPs on real-world datasets with up to five million examples.
Transformer-based method discovers objects from images without labels.
problem Discovering objects in images without labeled data.
method Graph-based approach using self-supervised transformer features and normalized graph-cut.
result Significantly boosts performance in unsupervised object discovery.
t-SNE loses important features in data visualization.
problem t-SNE's loss of important features in data visualization.
method Established mathematical framework to understand t-SNE's loss in different scenarios.
result t-SNE loses important features of data in various scenarios.
We determine the sample complexity of pure exploration bandit problems with multiple good answers. We derive a lower bound using a new game equilibrium argument. We show how continuity and convexity properties of single-answer problems ensures that the Track-and-Stop algorithm has asymptotically optimal sample complexi…
A simple example shows that losing all money is compatible with a very high Sharpe ratio (as computed after losing all money). However, the only way that the Sharpe ratio can be high while losing money is that there is a period in which all or almost all money is lost. This note explores the best achievable Sharpe and …
Raiders of the Lost Architecture: Kernels for Bayesian Optimization in Conditional Parameter Spacesstat.ML
In practical Bayesian optimization, we must often search over structures with differing numbers of parameters. For instance, we may wish to search over neural network architectures with an unknown number of layers. To relate performance data gathered for different architectures, we define a new kernel for conditional p…
We formulate a sufficient condition for the existence of a consistent price system (CPS), which is weaker than the conditional full support condition (CFS) introduced by Guasoni, Rasonyi, and Schachermayer [Ann. Appl. Probab., 18(2008), pp. 491-520] . We use the new condition to show the existence of CPSs for certain p…
CUDA CTDR tackles unsupervised domain adaptation without domain alignment.
problem Lack of direct methods for unlabeled target domain classification.
method Jointly learns CTDR on source and target distributions using contradistinguish loss and supervised loss.
result CUDA CTDR achieves state-of-the-art results on various domain adaptation datasets.
Evaluating the Financial Market Function in Prewar Japan using a Time-Varying Parameter Modelq-fin.ST
This study evaluates prewar Japanese financial market efficiency using time-varying models.
problem Determining when prewar Japanese financial market lost its price formation function.
method Time-varying parameter model, generalized least squares-based time-varying vector autoregressive model.
result The prewar Japanese financial market lost its price formation function in 1932.
We highlight a pitfall when applying stochastic variational inference to general Bayesian networks. For global random variables approximated by an exponential family distribution, natural gradient steps, commonly starting from a unit length step size, are averaged to convergence. This useful insight into the scaling of…
Recovering edge activities from node activity data in temporal networks.
problem Recovering lost edge activity data from aggregated node activity data in temporal networks.
method Analyzing the relationship between edge activity and node activity data, using both theoretical and empirical methods to show recovery is possible and under what conditions.
result Recovery of edge activities from node activities is possible with surprising accuracy, even when network density increases.
Gaussian processes (GPs) provide a powerful non-parametric framework for reasoning over functions. Despite appealing theory, its superlinear computational and memory complexities have presented a long-standing challenge. State-of-the-art sparse variational inference methods trade modeling accuracy against complexity. H…
Squeezing bottlenecks: exploring the limits of autoencoder semantic representation capabilitiescs.IR
We present a comprehensive study on the use of autoencoders for modelling text data, in which (differently from previous studies) we focus our attention on the following issues: i) we explore the suitability of two different models bDA and rsDA for constructing deep autoencoders for text data at the sentence level; ii)…
Generative adversarial nets (GANs) have generated a lot of excitement. Despite their popularity, they exhibit a number of well-documented issues in practice, which apparently contradict theoretical guarantees. A number of enlightening papers have pointed out that these issues arise from unjustified assumptions that are…
Random matrix models generalize to Group Field Theories (GFT) whose Feynman graphs are dual to gluings of higher dimensional simplices. It is generally assumed that GFT graphs are always dual to pseudo manifolds. In this paper we prove that already in dimension three (and in all higher dimensions), this is not true due…
Graph smoothing can improve learning performance by restoring lost information.
problem Graph Neural Networks (GNNs) can oversmooth, losing important information.
method Analyzing simplified linear GNNs with mean aggregation, showing benefits up to a certain point.
result Graph smoothing can restore lost information, improving both regression and classification.