We introduce a conceptually simple and scalable framework for continual learning domains where tasks are learned sequentially. Our method is constant in the number of parameters and is designed to preserve performance on previously encountered tasks while accelerating learning progress on subsequent problems. This is a…
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.
168,982 papers · 148 categories
Trend · papers per month
48 results for “Knowledge Progression”
PS-KD distills a model's own knowledge to soften hard targets during training.
problem Improving generalization of deep neural networks by softening hard targets.
method Progressive self-knowledge distillation (PS-KD) that progressively distills a model's own knowledge to soften hard targets.
result PS-KD improves accuracy and provides high quality of confidence estimates in terms of calibration and ordinal ranking.
Extracting a curriculum from a teacher network improves distillation efficiency.
problem Efficiently training a small network using a large teacher network's output.
method Random projection of teacher network's hidden representations to progressively train the student network.
result Extracted curriculum significantly outperforms one-shot distillation and achieves similar performance to progressive distillation.
The concept of progress has characterized human society from millennia. However, this concept is elusive and too often given for certain. The goal of this paper is to suggest a general definition of human progress that satisfies, whenever possible the conditions of independence, generality, epistemological applicabilit…
This paper improves disentanglement in VAEs by progressively learning hierarchical representations.
problem Compromised disentanglement in VAEs due to high-level abstraction extraction.
method Progressive learning of independent hierarchical representations from high to low levels.
result Improved disentanglement demonstrated on two benchmark datasets using new metrics.
LHM integrates expert ODEs with neural ODEs for disease progression prediction.
problem Predicting disease progression under medications using limited data.
method Integrating expert-designed ODEs with machine-learned Neural ODEs.
result LHM consistently outperforms previous methods, especially in small sample regimes.
New equations reveal how cylinder power in progressive lenses depends on geodesic curvature.
problem Current understanding of cylinder power in progressive lenses is incomplete.
method Derived complete compatibility equations for spatially-varying curvature surfaces.
result Cylinder power depends on geodesic curvature, not just principal curvature.
PAS method improves UDA by progressively refining subspaces for reliable pseudo-labels.
problem Mitigating mode collapse in unsupervised domain adaptation.
method Progressive Adaptation of Subspaces (PAS) approach.
result PAS effectively mitigates mode collapse and improves performance in UDA and PDA.
New embedding method in function spaces improves expressiveness.
problem Enhancing expressiveness in knowledge graph embeddings.
method Employing polynomial functions and neural networks with varying layer complexities.
result Improved expressiveness and more degrees of freedom in entity representation.
KT models improved slightly with synthetic student data.
problem Limited access to real student data and lack of diversity in public datasets.
method Simulated student data using three statistical strategies and tested on KT baselines.
result Synthetic data can lead to similar performance as real data.
AlphaZero reveals new chess concepts learnable by top experts.
problem Extracting and understanding hidden knowledge from AI systems.
method Proposed method to extract new chess concepts from AlphaZero.
result Top chess grandmasters show improvements in learning new concepts.
Survey explores how transfer learning improves deep reinforcement learning.
problem Challenges in reinforcement learning efficiency and effectiveness.
method Categorizes and analyzes transfer learning approaches.
result Transfer learning enhances reinforcement learning performance.
Recent progress in artificial intelligence (AI) has renewed interest in building systems that learn and think like people. Many advances have come from using deep neural networks trained end-to-end in tasks such as object recognition, video games, and board games, achieving performance that equals or even beats humans …
We define general linguistic intelligence as the ability to reuse previously acquired knowledge about a language's lexicon, syntax, semantics, and pragmatic conventions to adapt to new tasks quickly. Using this definition, we analyze state-of-the-art natural language understanding models and conduct an extensive empiri…
Bernstein processes are Brownian diffusions that appear in Euclidean Quantum Mechanics. Knowledge of the symmetries of the Hamilton-Jacobi-Bellman equation associated with these processes allows one to obtain relations between stochastic processes (Lescot-Zambrini, Progress in Probability, vols 58 and 59). More recentl…
HOPE uses Hilbert space to deconstruct deep network representations.
problem Deconstructing learned representations in deep networks is challenging.
method Introduces Hilbert Operator for Progressive Encoding (HOPE) to deconstruct network weights.
result HOPE provides an unbiased approach to network compression and fine-tuning.
PSI-KT improves KT accuracy and interpretability in learning materials.
problem Optimizing learning materials selection and timing for understanding and retention.
method Hierarchical generative approach using Bayesian inference.
result Superior multi-step predictive accuracy and scalable inference.
Knowledge Matters: Importance of Prior Information for Optimization [7], by Gulcehre et. al., sought to establish the limits of current black-box, deep learning techniques by posing problems which are difficult to learn without engineering knowledge into the model or training procedure. In our work, we completely solve…
This paper introduces self-paced task selection to multitask learning, where instances from more closely related tasks are selected in a progression of easier-to-harder tasks, to emulate an effective human education strategy, but applied to multitask machine learning. We develop the mathematical foundation for the appr…
OpenHAIV integrates OOD detection and incremental learning for open-world models.
problem Challenges in open-world recognition, especially in model knowledge updates and OOD detection.
method Unified pipeline combining OOD detection, new class discovery, and incremental fine-tuning.
result Models can autonomously acquire and update knowledge in open-world environments.
Machine reading using differentiable reasoning models has recently shown remarkable progress. In this context, End-to-End trainable Memory Networks, MemN2N, have demonstrated promising performance on simple natural language based reasoning tasks such as factual reasoning and basic deduction. However, other tasks, namel…
Purpose: Machine learning is broadly used for clinical data analysis. Before training a model, a machine learning algorithm must be selected. Also, the values of one or more model parameters termed hyper-parameters must be set. Selecting algorithms and hyper-parameter values requires advanced machine learning knowledge…
Despite the advancement of supervised image recognition algorithms, their dependence on the availability of labeled data and the rapid expansion of image categories raise the significant challenge of zero-shot learning. Zero-shot learning (ZSL) aims to transfer knowledge from labeled classes into unlabeled classes to r…
DBULL learns new clusters without forgetting past knowledge in streaming unlabelled data.
problem Challenges in Unsupervised Lifelong Learning with evolving data distributions and class labels.
method Bayesian framework for incremental learning, Deep Bayesian Unsupervised Lifelong Learning (DBULL) algorithm, knowledge preservation mechanism, automatic cluster discovery.
result DBULL can progressively discover new clusters without forgetting past knowledge in unlabelled data.
Framework predicts patient risk progression over time.
problem Predicting how patient risk changes over time.
method Supervised contrastive learning framework with embedding properties.
result Framework outperforms baselines in mortality and cognitive impairment datasets.
Proposes a method to compress deep networks using adversarial training and attention mechanisms.
problem Lack of efficient methods to compress deep networks while preserving important information.
method Adversarial training with task-driven attention mechanism for effective intermediate supervision.
result Demonstrates superior performance on benchmark datasets compared to state-of-the-art methods.
ProSelfLC improves robustness of deep neural networks by automatically deciding trust in predictions.
problem Training robust deep neural networks requires addressing issues like label noise and low entropy predictions.
method ProSelfLC progressively increases trust in predicted labels over time, considering entropy and learning time.
result ProSelfLC demonstrates improved robustness in both clean and noisy settings through empirical validation.
AI uses KGs to assess economic impact of selective lockdowns on Italian companies.
problem Impact of selective lockdowns on Italian companies' economic stability.
method Automated Reasoning and Knowledge Graphs to analyze company networks.
result Identifies strategic companies at risk of takeover during lockdowns.
GENE tackles sparse reward in RL by generating states to explore and exploit.
problem Sparse reward in reinforcement learning.
method Generative Exploration and Exploitation (GENE) method.
result GENE significantly outperforms existing methods in tasks with binary rewards.
Learning from many real-world datasets is limited by a problem called the class imbalance problem. A dataset is imbalanced when one class (the majority class) has significantly more samples than the other class (the minority class). Such datasets cause typical machine learning algorithms to perform poorly on the classi…
QuantAgent learns trading signals through self-improvement.
problem Building domain-specific knowledge for LLMs in quantitative investment.
method Two-layer loop approach: inner loop refines responses, outer loop tests and learns.
result QuantAgent approximates optimal trading behavior with provable efficiency.
While recent progress has spawned very powerful machine learning systems, those agents remain extremely specialized and fail to transfer the knowledge they gain to similar yet unseen tasks. In this paper, we study a simple reinforcement learning problem and focus on learning policies that encode the proper invariances …
Deep Neural Networks have achieved huge success at a wide spectrum of applications from language modeling, computer vision to speech recognition. However, nowadays, good performance alone is not sufficient to satisfy the needs of practical deployment where interpretability is demanded for cases involving ethics and mis…
We compare the acquisition of knowledge in humans and machines. Research from the field of developmental psychology indicates, that human-employed hypothesis are initially guided by simple rules, before evolving into more complex theories. This observation is shared across many tasks and domains. We investigate whether…
Meta-learning shows negative transfer between tasks, which MetaCRL addresses.
problem Negative transfer between tasks in meta-learning.
method Structural Causal Models (SCMs) and MetaCRL to eliminate task confounders.
result MetaCRL achieves state-of-the-art performance in various benchmark datasets.
This paper proposes a method to compress and adapt CNNs for real-world applications.
problem Differences in data distributions and high computational costs limit CNN adoption.
method Joint optimization of CNNs for unsupervised domain adaptation and knowledge distillation.
result The proposed method achieves the highest accuracy with comparable or lower time complexity.
Galactica learns from scientific literature to help researchers.
problem Information overload in scientific literature makes it hard to find useful insights.
method Trained on a large corpus of scientific papers, reference material, and knowledge bases.
result Outperforms existing models on various scientific tasks, including LaTeX equations and mathematical reasoning.
Recent progress in deep learning is revolutionizing the healthcare domain including providing solutions to medication recommendations, especially recommending medication combination for patients with complex health conditions. Existing approaches either do not customize based on patient health history, or ignore existi…
A Convolutional Neural Network was used to predict kidney function in patients with chronic kidney disease from high-resolution digital pathology scans of their kidney biopsies. Kidney biopsies were taken from participants of the NEPTUNE study, a longitudinal cohort study whose goal is to set up infrastructure for obse…
AxCell automates results extraction from machine learning papers.
problem Difficulty in tracking progress in machine learning due to many papers.
method AxCell uses table segmentation and learns structural knowledge to extract results.
result AxCell significantly improves results extraction compared to existing methods.
A Survey of Large Language Models for Financial Applications: Progress, Prospects and Challengesq-fin.GN
Survey of LLMs in finance tasks, highlighting progress and challenges.
problem Transforming financial practices with advanced LLMs.
method Exploration of various financial tasks, categorization, and analysis of methodologies.
result Unlocking novel opportunities for financial applications with LLMs.
The abstract warns against flawed empirical research in machine learning.
problem Flawed empirical research in machine learning leading to unreliable results.
method Call for more awareness of experimental knowledge plurality and epistemic limitations.
result Current empirical machine learning research should be exploratory, not confirmatory.
Knowledge Graph Embedding with Electronic Health Records Data via Latent Graphical Block Modelstat.ML
Proposes a method to derive knowledge graphs from EHR data.
problem Challenges in deriving generalizable knowledge from EHR data.
method Infer conditional dependency structure via a latent graphical block model (LGBM).
result Perfect recovery of block structure demonstrated.
AutoKE automates embedding physical knowledge into neural networks for complex engineering problems.
problem Complex physical equations in engineering problems.
method AutoKE framework using deep neural networks, equation parsing, automatic differentiation, adaptive weights, and NAS.
result Automatically embeds physical knowledge into neural networks for complex equations efficiently.
The paper characterizes the efficiency of transferring knowledge from a teacher to a student classifier over finite domains.
problem Characterizing the statistical efficiency of knowledge transfer over finite domains.
method Three progressive levels of privileged information: hard labels, teacher probabilities, and soft labels. Novel empirical loss functions used to achieve the fundamental limits.
result Achieving the fundamental limits of knowledge transfer through specific levels of privileged information and novel loss functions.
SpanishTinyRoBERTa distills large Spanish models into efficient question-answering models.
problem Efficient Spanish question-answering models for resource-constrained environments.
method Knowledge distillation from large Spanish language models onto a smaller model.
result SpanishTinyRoBERTa achieves comparable performance to large models with faster inference.
In this article, we investigate when the set of primitive geodesic lengths on a Riemannian manifold have arbitrarily long arithmetic progressions. We prove that in the space of negatively curved metrics, a metric having such arithmetic progressions is quite rare. We introduce almost arithmetic progressions, a coarsific…
Study evaluates large language models' ability to understand probabilistic real-world distributions.
problem Understanding how LLMs grasp probabilistic knowledge of real-world distributions.
method Developed a benchmark to test LLMs' ability to learn and represent empirical distributions across various domains.
result LLMs perform poorly in understanding real-world statistics and do not naturally internalize these distributions.