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.
OpenHAIV integrates OOD detection and incremental learning for open-world models.
This paper reviews information theory in open-world machine learning.
Neural approach enhances AI trustworthiness, generalization, and robustness.
This paper reviews FSL for open-world learning, addressing uncertainties and dynamic conditions.
This paper evaluates knowledge graph completion models under the open-world assumption, revealing unexpected behavior of metrics.
OwMatch improves open-world semi-supervised learning by self-labeling and consistency.
A large body of recent work has investigated the phenomenon of evasion attacks using adversarial examples for deep learning systems, where the addition of norm-bounded perturbations to the test inputs leads to incorrect output classification. Previous work has investigated this phenomenon in closed-world systems where …
This work bridges continual learning, active learning, and open set recognition in deep neural networks.
In real-world recognition/classification tasks, limited by various objective factors, it is usually difficult to collect training samples to exhaust all classes when training a recognizer or classifier. A more realistic scenario is open set recognition (OSR), where incomplete knowledge of the world exists at training t…
Modern machine learning systems such as image classifiers rely heavily on large scale data sets for training. Such data sets are costly to create, thus in practice a small number of freely available, open source data sets are widely used. We suggest that examining the geo-diversity of open data sets is critical before …
Random forest can be adapted for open-set recognition with improved performance.
BoFire optimizes chemistry experiments using Bayesian Optimization.
Open-FinLLMs tackle financial tasks with multimodal capabilities.
As we enter into the big data age and an avalanche of images have become readily available, recognition systems face the need to move from close, lab settings where the number of classes and training data are fixed, to dynamic scenarios where the number of categories to be recognized grows continuously over time, as we…
WILD-SCAV benchmarks AI in complex 3D FPS environments.
DreamerV3 learns diverse tasks with a single configuration.
COME replaces entropy minimization to prevent model collapse.
Submanifolds of finite type were introduced by the author during the late 1970s. The first results on this subject had been collected in author's book [Total mean curvature and sub manifolds of finite type, World Scientific, NJ, 1984]. A list of ten open problems and three conjectures on submanifolds of finite type was…
In a real-world setting, visual recognition systems can be brought to make predictions for images belonging to previously unknown class labels. In order to make semantically meaningful predictions for such inputs, we propose a two-step approach that utilizes information from knowledge graphs. First, a knowledge-graph r…
For a broad variety of critical applications, it is essential to know how confident a classification prediction is. In this paper, we discuss the drawbacks of softmax to calculate class probabilities and to handle uncertainty in Bayesian neural networks. We introduce a new kind of prediction layer called radial predict…
Convolutional neural networks are commonly used to control the steering angle for autonomous cars. Most of the time, multiple long range cameras are used to generate lateral failure cases. In this paper we present a novel model to generate this data and label augmentation using only one short range fisheye camera. We p…
Survey on offline RL methods for real-world applications.
We present a framework capable of tackilng the problem of continual object recognition in a setting which resembles that under whichhumans see and learn. This setting has a set of unique characteristics:it assumes an egocentric point-of-view bound to the needs of a singleperson, which implies a relatively low diversity…
Email messages have been an important mode of communication, not only for work, but also for social interactions and marketing. When messages have time sensitive information, it becomes relevant for the sender to know what is the expected time within which the email will be read by the recipient. In this paper we use a…
Many real-world engineering problems rely on human preferences to guide their design and optimization. We present PrefOpt, an open source package to simplify sequential optimization tasks that incorporate human preference feedback. Our approach extends an existing latent variable model for binary preferences to allow f…
OpenViewer tackles multi-view learning challenges with interpretability and generalization.
The abstract discusses open data resources for studying and controlling the spread of COVID-19.
DreamerV2 learns Atari game behaviors from a world model, achieving human-level performance.
Open dataset and pipeline for realistic OPE research.
Optimizes control interventions in real-world networks using deep-learning and network science.
ApolloRL offers a platform for RL research in autonomous driving.
Analyzes Indian commercial dynamism using time series data.
Goldbach conjecture is one of the most famous open mathematical problems. It states that every even number, bigger than two, can be presented as a sum of 2 prime numbers. % In this work we present a deep learning based model that predicts the number of Goldbach partitions for a given even number. Surprisingly, our mode…
We show that tree almost automorphism groups, including Neretin groups, satisfy the analogue of the -finiteness condition in the world of totally disconnected groups: They possess a cellular action on a contractible cellular complex such that the stabilizers are open and compact and the restriction of the act…
In conventional domain adaptation, a critical assumption is that there exists a fully labeled domain (source) that contains the same label space as another unlabeled or scarcely labeled domain (target). However, in the real world, there often exist application scenarios in which both domains are partially labeled and n…
This paper analyzes and improves active learning techniques for real-world projects.
We present MILABOT: a deep reinforcement learning chatbot developed by the Montreal Institute for Learning Algorithms (MILA) for the Amazon Alexa Prize competition. MILABOT is capable of conversing with humans on popular small talk topics through both speech and text. The system consists of an ensemble of natural langu…
Often, when dealing with real-world recognition problems, we do not need, and often cannot have, knowledge of the entire set of possible classes that might appear during operational testing. In such cases, we need to think of robust classification methods able to deal with the "unknown" and properly reject samples belo…
CGDL improves open set recognition by learning conditional Gaussian distributions.
Proposes a new framework for open set recognition using conditional probabilistic generative models.
Uncertainty Toolbox aids in assessing and improving uncertainty quantification in machine learning.
The classification of textual data often yields important information. Most classifiers work in a closed world setting where the classifier is trained on a known corpus, and then it is tested on unseen examples that belong to one of the classes seen during training. Despite the usefulness of this design, often there is…
In many real-world sequential decision making problems, the number of available actions (decisions) can vary over time. While problems like catastrophic forgetting, changing transition dynamics, changing rewards functions, etc. have been well-studied in the lifelong learning literature, the setting where the action set…
The research community has increasing interest in autonomous driving research, despite the resource intensity of obtaining representative real world data. Existing self-driving datasets are limited in the scale and variation of the environments they capture, even though generalization within and between operating regio…
This paper describes the design, implementation, and successful use of the Bristol Stock Exchange (BSE), a novel minimal simulation of a centralised financial market, based on a Limit Order Book (LOB) such as is common in major stock exchanges. Construction of BSE was motivated by the fact that most of the world's majo…
U-aggregation combines multiple models without labels for better risk prediction.
ATOM improves robust OOD detection by mining informative auxiliary examples.
The Boolean Satisfiability (SAT) problem is the canonical NP-complete problem and is fundamental to computer science, with a wide array of applications in planning, verification, and theorem proving. Developing and evaluating practical SAT solvers relies on extensive empirical testing on a set of real-world benchmark f…