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.
Analyzes how uncertainty in financial networks affects stability.
ProxySHAP approximates Shapley and Banzhaf interactions efficiently.
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 …
Deep Reinforcement Learning (DRL) has become a powerful strategy to solve complex decision making problems based on Deep Neural Networks (DNNs). However, it is highly data demanding, so unfeasible in physical systems for most applications. In this work, we approach an alternative Interactive Machine Learning (IML) stra…
The search for higher-order feature interactions that are statistically significantly associated with a class variable is of high relevance in fields such as Genetics or Healthcare, but the combinatorial explosion of the candidate space makes this problem extremely challenging in terms of computational efficiency and p…
LLMs struggle with zero-shot annotation tasks due to model-internalized priors.
Various domain users are increasingly leveraging real-time social media data to gain rapid situational awareness. However, due to the high noise in the deluge of data, effectively determining semantically relevant information can be difficult, further complicated by the changing definition of relevancy by each end user…
Belief Propagation (BP) is one of the most popular methods for inference in probabilistic graphical models. BP is guaranteed to return the correct answer for tree structures, but can be incorrect or non-convergent for loopy graphical models. Recently, several new approximate inference algorithms based on cavity distrib…
We consider the problem of inferring the interactions between a set of N binary variables from the knowledge of their frequencies and pairwise correlations. The inference framework is based on the Hopfield model, a special case of the Ising model where the interaction matrix is defined through a set of patterns in the …
Leveraging weak or noisy supervision for building effective machine learning models has long been an important research problem. Its importance has further increased recently due to the growing need for large-scale datasets to train deep learning models. Weak or noisy supervision could originate from multiple sources i…
Inferring causal interactions from observed data is a challenging problem, especially in the presence of measurement noise. To alleviate the problem of spurious causality, Haufe et al. (2013) proposed to contrast measures of information flow obtained on the original data against the same measures obtained on time-rever…
We present an approach to interactive-predictive neural machine translation that attempts to reduce human effort from three directions: Firstly, instead of requiring humans to select, correct, or delete segments, we employ the idea of learning from human reinforcements in form of judgments on the quality of partial tra…
DisCor corrects reinforcement learning issues by re-weighting collected data.
IAL uses interactive learning to improve model performance with minimal human feedback.
Deep neural networks (DNNs) are increasingly powering high-stakes applications such as autonomous cars and healthcare; however, DNNs are often treated as "black boxes" in such applications. Recent research has also revealed that DNNs are highly vulnerable to adversarial attacks, raising serious concerns over deploying …
In human-in-the-loop machine learning, the user provides information beyond that in the training data. Many algorithms and user interfaces have been designed to optimize and facilitate this human--machine interaction; however, fewer studies have addressed the potential defects the designs can cause. Effective interacti…
Renormalization in neural networks linked to quantum field theory.
A new framework for offline RL improves policy flexibility and regularity.
New method provides fine-grained feedback on interactive student programs.
Not all types of supervision signals are created equal: Different types of feedback have different costs and effects on learning. We show how self-regulation strategies that decide when to ask for which kind of feedback from a teacher (or from oneself) can be cast as a learning-to-learn problem leading to improved cost…
The paper optimizes exceptions in a statistical production system using machine learning.
ECBMs unify concept-based interpretations in deep learning models.
We expand the item response theory to study the case of "cheating students" for a set of exams, trying to detect them by applying a greedy algorithm of inference. This extended model is closely related to the Boltzmann machine learning. In this paper we aim to infer the correct biases and interactions of our model by c…
Machine learning systems increasingly depend on pipelines of multiple algorithms to provide high quality and well structured predictions. This paper argues interaction effects between clustering and prediction (e.g. classification, regression) algorithms can cause subtle adverse behaviors during cross-validation that m…
Model analyzes trading frictions in cap-and-trade markets, showing how they interact to affect market effectiveness.
Insights in power grid pixel maps (PGPMs) refer to important facility operating states and unexpected changes in the power grid. Identifying insights helps analysts understand the collaboration of various parts of the grid so that preventive and correct operations can be taken to avoid potential accidents. Existing sol…
Introduce a variance-weighted batch distribution for diverse sampling in diffusion models.
Behavioral cloning reduces policy learning to supervised learning by training a discriminative model to predict expert actions given observations. Such discriminative models are non-causal: the training procedure is unaware of the causal structure of the interaction between the expert and the environment. We point out …
Scene understanding and semantic segmentation are at the core of many computer vision tasks, many of which, involve interacting with humans in potentially dangerous ways. It is therefore paramount that techniques for principled design of robust models be developed. In this paper, we provide analytic and empirical evide…
Develops NFCF to reduce gender bias in social media recommendation systems.
Computational approaches to drug discovery can reduce the time and cost associated with experimental assays and enable the screening of novel chemotypes. Structure-based drug design methods rely on scoring functions to rank and predict binding affinities and poses. The ever-expanding amount of protein-ligand binding an…
This work describes simple and efficient algorithms for interactively learning non-binary concepts in the learning from random counter-examples (LRC) model. Here, learning takes place from random counter-examples that the learner receives in response to their proper equivalence queries. In this context, the learning ti…
Proposes a two-stage method for testing variable interactions with FDR control.
Safe offline RL for chemical reactors using input convex neural networks.
New algorithms for interactive learning match minimax bounds efficiently.
In many real-world reinforcement learning applications, access to the environment is limited to a fixed dataset, instead of direct (online) interaction with the environment. When using this data for either evaluation or training of a new policy, accurate estimates of discounted stationary distribution ratios -- correct…
Individual choices are either based on personal experience or on information provided by peers. The latter case, causes individuals to conform to the majority in their neighborhood. Such herding behavior may be very efficient in aggregating disperse private information, thereby revealing the optimal choice. However if …
Learning compact and interpretable representations is a very natural task, which has not been solved satisfactorily even for simple binary datasets. In this paper, we review various ways of composing experts for binary data and argue that competitive forms of interaction are best suited to learn low-dimensional represe…
Dynamic Vine Copulas detect and quantify time-varying higher-order interactions in multivariate systems.
New construction reveals SU(2)-flavor fields in heterotic M5-brane model.
The anholonomic frame method is generalized for non--Riemannian gravity models defined by string corrections to the general relativity and metric-affine gravity (MAG) theories. Such spacetime configurations are modeled as metric-affine spaces provided with generic off-diagonal metrics (which can not be diagonalized by …
New RL algorithms correct bias in dynamic data analysis.
Model discovers causal relationships from video data of physical systems.
Most multi-class classifiers make their prediction for a test sample by scoring the classes and selecting the one with the highest score. Analyzing these prediction scores is useful to understand the classifier behavior and to assess its reliability. We present an interactive visualization that facilitates per-class an…
Enhances knowledge graph completion with mixed geometry tensor factorization.
We consider the Degree-Corrected Stochastic Block Model (DC-SBM): a random graph on nodes, having i.i.d. weights (possibly heavy-tailed), partitioned into asymptotically equal-sized clusters. The model parameters are two constants and the finite second moment of the weights $Φ^{…
In this paper we introduce a new neural architecture for sorting unordered sequences where the correct sequence order is not easily defined but must rather be inferred from training data. We refer to this architecture as OrderNet and describe how it was constructed to be naturally permutation equivariant while still al…
In this comment on "Solving Statistical Mechanics Using Variational Autoregressive Networks" by Wu et al., we propose a subtle yet powerful modification of their approach. We show that the inherent sampling error of their method can be corrected by using neural network-based MCMC or importance sampling which leads to a…