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.
Improved anomaly detection for launch vehicle propulsion systems using LSTM and statistical relabeling.
New method improves meta-reinforcement learning efficiency.
Rewriting history improves RL algorithms for solving multiple tasks.
Identifies minimal training subset to flip a prediction.
Cincer cleans both new and past data by identifying and relabeling suspicious and counter-examples.
Generalized Hindsight improves RL by reusing data from one task for another.
Paper proposes methods to improve SVM classifiers in noisy data scenarios.
The study examines how permutation-based optimization performance varies across different function representations.
Algorithm learns new tasks efficiently from past experience.
Study matches two noisy point clouds with geometric transformations and relabeling.
Deep neural networks (DNNs) are powerful tools in computer vision tasks. However, in many realistic scenarios label noise is prevalent in the training images, and overfitting to these noisy labels can significantly harm the generalization performance of DNNs. We propose a novel technique to identify data with noisy lab…
This work improves RL for complex robotic tasks by guiding exploration with task-specific goal distributions.
When Daan Krammer and Stephen Bigelow independently proved that braid groups are linear, they used the Lawrence-Krammer-Bigelow representation for generic values of its variables q and t. The t variable is closely connected to the traditional Garside structure of the braid group and plays a major role in Krammer's alge…
A new permutation method improves two-sample testing power.
PEAR dynamically reconfigures agent roles to prevent persistent biases in multi-agent debates.
Language creates a compact representation of the world and allows the description of unlimited situations and objectives through compositionality. While these characterizations may foster instructing, conditioning or structuring interactive agent behavior, it remains an open-problem to correctly relate language underst…
When learning from positive and unlabelled data, it is a strong assumption that the positive observations are randomly sampled from the distribution of conditional on , where X stands for the feature and Y the label. Most existing algorithms are optimally designed under the assumption. However, for many real…
FairUDT uses uplift decision trees to detect and mitigate discrimination in training data.
Proposes autoencoding with random forests using spectral graph theory.
We propose Generative Well-intentioned Networks (GWINs), a novel framework for increasing the accuracy of certainty-based, closed-world classifiers. A conditional generative network recovers the distribution of observations that the classifier labels correctly with high certainty. We introduce a reject option to the cl…
SymmPI predicts unobserved values under group symmetries, improving over existing methods.
Many machine learning systems rely on data collected in the wild from untrusted sources, exposing the learning algorithms to data poisoning. Attackers can inject malicious data in the training dataset to subvert the learning process, compromising the performance of the algorithm producing errors in a targeted or an ind…
Study efficient interactive learning for structured outputs with reliable computation.
We propose new positive definite kernels for permutations. First we introduce a weighted version of the Kendall kernel, which allows to weight unequally the contributions of different item pairs in the permutations depending on their ranks. Like the Kendall kernel, we show that the weighted version is invariant to rela…
Improves k-NN for monotonic data with robustness against noise.
We survey the role of symmetry in diffeomorphic registration of landmarks, curves, surfaces, images and higher-order data. The infinite dimensional problem of finding correspondences between objects can for a range of concrete data types be reduced resulting in compact representations of shape and spatial structure. Th…
Many popular network models rely on the assumption of (vertex) exchangeability, in which the distribution of the graph is invariant to relabelings of the vertices. However, the Aldous-Hoover theorem guarantees that these graphs are dense or empty with probability one, whereas many real-world graphs are sparse. We prese…
Sparse reward is one of the most challenging problems in reinforcement learning (RL). Hindsight Experience Replay (HER) attempts to address this issue by converting a failed experience to a successful one by relabeling the goals. Despite its effectiveness, HER has limited applicability because it lacks a compact and un…
Linear models can be poisoned by shifting a fraction of one class's data, revealing scaling laws and weight alignment.
Novel discretization of Euler equations for incompressible fluids.
Deep neural networks have achieved impressive success in large-scale visual object recognition tasks with a predefined set of classes. However, recognizing objects of novel classes unseen during training still remains challenging. The problem of detecting such novel classes has been addressed in the literature, but mos…
Study investigates one-shot semi-supervised learning for image classification.
For an autonomous agent to fulfill a wide range of user-specified goals at test time, it must be able to learn broadly applicable and general-purpose skill repertoires. Furthermore, to provide the requisite level of generality, these skills must handle raw sensory input such as images. In this paper, we propose an algo…
CNNs improve transient detection in DES-SN images.
A new measure of causal influence quantifies intrinsic contributions in DAGs.
Current reinforcement learning (RL) algorithms can be brittle and difficult to use, especially when learning goal-reaching behaviors from sparse rewards. Although supervised imitation learning provides a simple and stable alternative, it requires access to demonstrations from a human supervisor. In this paper, we study…
Cold posteriors improve Bayesian neural networks by reducing overestimation of aleatoric uncertainty.
New MCMC method tackles label-switching problem for clustering.
We tackle the Multi-task Batch Reinforcement Learning problem. Given multiple datasets collected from different tasks, we train a multi-task policy to perform well in unseen tasks sampled from the same distribution. The task identities of the unseen tasks are not provided. To perform well, the policy must infer the tas…
This paper aims to incorporate passive symmetries in machine learning for better generalization.
We present relay policy learning, a method for imitation and reinforcement learning that can solve multi-stage, long-horizon robotic tasks. This general and universally-applicable, two-phase approach consists of an imitation learning stage that produces goal-conditioned hierarchical policies, and a reinforcement learni…
Clustering ensemble is one of the most recent advances in unsupervised learning. It aims to combine the clustering results obtained using different algorithms or from different runs of the same clustering algorithm for the same data set, this is accomplished using on a consensus function, the efficiency and accuracy of…
Study shows label errors impact model disparity metrics, proposing mitigation methods.
New uniformity tester ensures consistent results across different samples.
We propose a framework, named Aggregated Wasserstein, for computing a dissimilarity measure or distance between two Hidden Markov Models with state conditional distributions being Gaussian. For such HMMs, the marginal distribution at any time spot follows a Gaussian mixture distribution, a fact exploited to softly matc…
Proposes DeGLIF to denoise graph data for label noise robustness.
This work relaxes GNN symmetries to approximate automorphisms, improving model performance.
Neural network for subgraph similarity computation with pruning.