Gradient surgery improves multi-task learning efficiency.
problem Challenges in sharing structure across multiple tasks.
method Gradient projection onto normal plane of conflicting gradients.
result Substantial gains in efficiency and performance.
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.
169,051 papers · 148 categories
Trend · papers per month
48 results for “challenging tasks”
Multi-label Classification for Automatic Tag Prediction in the Context of Programming Challengescs.LG
This paper automates tagging programming challenge descriptions.
problem Tagging programming challenge descriptions is tedious for creators.
method Used machine and deep learning methods for automation.
result Deep learning methods outperform traditional IR approaches.
ADReSS Challenge at INTERSPEECH 2020 benchmarks speech recognition for Alzheimer's dementia.
problem Automated recognition of Alzheimer's dementia from spontaneous speech.
method Provides a benchmark speech dataset, defines two tasks (classification and regression), and presents baseline models.
result Demonstrates the feasibility of automated speech recognition for Alzheimer's dementia.
New approach allows deep learning to adapt to new tasks without explicit training.
problem How to reuse deep learning knowledge for new tasks without explicit training.
method Homoiconic Meta-Mapping (HoMM) that transforms task representations.
result Zero-shot remapping of behavior to adapt to new tasks.
MLFriend recommends useful prediction tasks for time-series data.
problem Automatically defining useful prediction tasks for event-driven time-series data.
method Generates all possible tasks, interacts with a data scientist to learn context, recommends useful tasks.
result MLFriend identifies 722 useful tasks out of 2885 generated tasks.
Paper discusses ASD challenge for machine condition monitoring.
problem Detecting unknown anomalous sounds without labeled data.
method Design and evaluation of a large-scale ASD dataset, novel approaches.
result Several novel approaches developed, evaluation results analyzed.
Plan2Explore learns new tasks efficiently through self-supervised planning.
problem Challenges in reinforcement learning, especially task-specific learning and sample efficiency.
method Self-supervised exploration and fast adaptation to new tasks through efficient planning.
result Plan2Explore outperforms prior methods in learning new tasks without supervision.
DCASE 2021 ASD task tackles domain-shifted anomalous sound detection.
problem Detecting unknown anomalous sounds under domain-shifted conditions.
method Ensemble of outlier exposure and inlier modeling detectors, feature learning from machine identification.
result Two types of remarkable approaches were adopted by top teams.
Task describes tagging audio clips from 41 categories.
problem Tagging audio clips from diverse categories.
method Baseline system using AudioSet labels.
result Demonstrates feasibility of general-purpose audio tagging.
THERMOMETER calibrates LLMs efficiently for diverse tasks.
problem Calibrating large language models is challenging due to computational and versatility issues.
method THERMOMETER learns an auxiliary model for calibrating a LLM using data from multiple tasks.
result THERMOMETER produces better-calibrated responses for new tasks.
DisCoRL combines state learning and policy distillation for continual reinforcement learning.
problem Learning multiple policies with a single model and inferring the correct policy at test time.
method Combining state representation learning and policy distillation.
result The policy can solve all tasks and automatically infer the correct one to run.
Challenge evaluates semantic code search using annotated corpus.
problem Evaluating relevant code from natural language queries.
method Release of CodeSearchNet Corpus and expert annotations.
result 99 queries with 4k relevance annotations for evaluation.
Method learns multi-stage tasks from single video, overcoming challenges of raw pixel learning and insufficient demonstrations.
problem Learning multi-stage vision-based tasks from a single video of a human performing the task.
method Learn primitive behaviors from video demonstrations and dynamically compose them to perform multi-stage tasks.
result Demonstrated learning of various tasks on real robots using raw pixel inputs and minimal demonstrations.
First ABAW 2020 Competition analyzes affective behavior tasks.
problem Automatic analysis of valence-arousal, basic expressions, and action units in real-world scenarios.
method Provided Aff-Wild2 database, described Challenges, evaluation metrics, and top-performing systems.
result Demonstrated the feasibility of automatic affective behavior analysis in real-world settings.
AuxiLearn combines auxiliary tasks into a single loss function.
problem Improving neural network performance on a main task using auxiliary tasks.
method Implicit differentiation to learn a network that combines auxiliary tasks into a single coherent objective function.
result AuxiLearn consistently outperforms competing methods in various tasks and domains.
New algorithm combines curriculum learning with HER for complex object manipulation tasks.
problem Learning complex sequential object manipulation tasks from scratch is challenging.
method Curriculum learning with Hindsight Experience Replay (HER) for recurrent object manipulation tasks.
result Significant improvement in learning sequential object manipulation tasks compared to vanilla-HER.
Agents struggle with solving tasks in new environments, but new models improve performance.
problem Rapid task-solving in novel environments.
method Developed EPNs to enable deep RL agents to plan over gathered knowledge.
result EPNs enable deep RL agents to excel at RTS, outperforming baselines by factors of 2-3.
In this thesis I explore challenging discrete energy minimization problems that arise mainly in the context of computer vision tasks. This work motivates the use of such "hard-to-optimize" non-submodular functionals, and proposes methods and algorithms to cope with the NP-hardness of their optimization. Consequently, t…
Direct Feedback Alignment performs well on diverse deep learning tasks and architectures.
problem The limitations of backpropagation in parallelizing and scaling to modern deep learning tasks.
method Direct Feedback Alignment approach applied to neural view synthesis, recommender systems, geometric learning, and natural language processing.
result Direct Feedback Alignment successfully trains a wide range of state-of-the-art deep learning architectures with performance close to fine-tuned backpropagation.
Improved disentanglement through learned feature aggregation.
problem Disentangling latent factors in images.
method Variational autoencoder trained on regionally aggregated feature maps from ImageNet.
result 2nd place in NeurIPS 2019 disentanglement challenge.
The Voice Conversion Challenge 2018: Promoting Development of Parallel and Nonparallel Methodseess.AS
We present the Voice Conversion Challenge 2018, designed as a follow up to the 2016 edition with the aim of providing a common framework for evaluating and comparing different state-of-the-art voice conversion (VC) systems. The objective of the challenge was to perform speaker conversion (i.e. transform the vocal ident…
Exploring with Sticky Mittens: Reinforcement Learning with Expert Interventions via Option Templatescs.LG
Framework uses expert intervention to solve long-horizon reinforcement learning tasks.
problem Long horizon robot learning tasks with sparse rewards.
method Option templates and expert intervention to enable high-level task understanding.
result Framework outperforms state-of-the-art approaches by two orders of magnitude.
Deep learning faces challenges in real-world tasks.
problem Challenges in applying deep learning to novel tasks without existing baselines.
method Case studies from research & development in conjunction with industry.
result Best practices for deep learning in practice.
MedAusbild team won ISIC challenge by classifying seven skin diseases.
problem Skin disease classification using medical images.
method Employed deep learning, specifically convolutional neural networks (CNNs), for seven skin disease classification.
result MedAusbild team won ISIC challenge 2018.
Meta-BO method clusters and learns from prior tasks to optimize heterogeneous functions.
problem Optimizing multiple functions with historical data and scalability issues.
method Clustering-based meta-learning, surrogate prototypes, adaptive weighting policies.
result Scalable and robust meta-BO method improves convergence to global optimum.
HSML tailors meta-learning knowledge to task clusters.
problem Handling task uncertainty and heterogeneity in meta-learning.
method Gradient-based HSML with hierarchical task clustering.
result HSML achieves state-of-the-art performance in few-shot learning.
DreamerV3 learns diverse tasks with a single configuration.
problem Generalizing reinforcement learning across multiple domains.
method World model and farsighted strategies.
result Outperforms specialized methods across 150 diverse tasks.
DCASE 2022 Task 2 tackles domain shifts in ASD for machine condition monitoring.
problem Domain shifts change acoustic characteristics, affecting ASD performance.
method Domain generalization techniques to detect anomalies across unknown domains.
result Two types of domain generalization techniques were identified and analyzed.
Federated learning poses new statistical and systems challenges in training machine learning models over distributed networks of devices. In this work, we show that multi-task learning is naturally suited to handle the statistical challenges of this setting, and propose a novel systems-aware optimization method, MOCHA,…
Paper fine-tunes LLMs for financial tasks using data fusion.
problem Improving LLMs for financial analysis tasks.
method Fine-tuned Llama3-8B and Mistral-7B using PEFT and LoRA, combined datasets for data fusion.
result Enhanced model performance across financial tasks.
The paper presents algorithms for diagnosing Pathological Myopia and detecting retinal structures.
problem Diagnosing Pathological Myopia and detecting retinal structures in fundus images.
method The approach uses Deep Learning techniques, including transfer learning with Xception and YOLO architecture.
result The method has shown satisfactory results in the Pathologic Myopia Challenge.
Mask-RCNN applied to ISIC 2018 lesion tasks.
problem Lesion boundary segmentation, attributes detection, and diagnosis.
method Mask-RCNN applied to ISIC 2018 challenge tasks with a trained model for task 1 and a simple voting procedure for task 3.
result Improved lesion diagnosis accuracy using Mask-RCNN.
We here summarize our experience running a challenge with open data for musical genre recognition. Those notes motivate the task and the challenge design, show some statistics about the submissions, and present the results.
Bayesian unlearning uses Bayes' rule to remove data from a model, but faces challenges in obtaining the exact posterior.
problem Removing data from a trained model while maintaining model accuracy.
method Uses Laplace approximation and Variational Inference to approximate the updated posterior.
result Insights on the applicability of Bayesian unlearning in practical scenarios for neural networks.
BeBold improves exploration in sparse-reward tasks by regulating visitation counts.
problem Efficient exploration in deep reinforcement learning under sparse rewards.
method Regulated difference of inverse visitation counts.
result BeBold solves 12 challenging tasks in MiniGrid with fewer steps than previous state-of-the-art.
MUMBO optimizes multiple tasks efficiently, even with low-cost related functions.
problem Efficiently optimizing multiple related functions with low-cost evaluations.
method Derives a novel multi-task version of entropy search.
result Robust performance with low computational overhead across various optimization challenges.
AI solutions matched prosthetic control goals in a challenge.
problem Matching time-varying velocity vectors in musculoskeletal models.
method Deep reinforcement learning approaches with various modifications.
result Many solutions used similar techniques but implemented unique modifications.
System tackles indeterminacies in automated audio captioning.
problem Word selection and sentence length indeterminacies in automated audio captioning.
method Solves caption generation and sub-indeterminacy problems through multi-task learning to estimate keywords and sentence length.
result Model achieved 20.7 SPIDEr score, significantly outperforming baseline.
Paper proposes a method to compose task-agnostic skills for solving new problems.
problem Learning task-specific policies for solving new problems.
method Deep reinforcement learning-based skill transfer and composition method.
result Method transfers skills to new problem settings and solves challenging environments with high data efficiency.
Researchers introduce datasets for cursive Japanese to ML community.
problem Engage ML community with classical Japanese literature datasets.
method Developed three datasets: Kuzushiji-MNIST, Kuzushiji-49, and Kuzushiji-Kanji.
result Introduced datasets focusing on cursive Japanese to ML community.
SAC improves deep RL by balancing reward and randomness.
problem High sample complexity and hyperparameter brittleness in RL.
method Maximum entropy framework, constrained optimization, temperature tuning.
result SAC achieves state-of-the-art performance and stability.
MERLIN tackles multi-objective task scheduling with hierarchical DRL, outperforming existing methods.
problem Optimizing multiple conflicting constraints in multi-objective task scheduling with varying queue sizes.
method Hierarchical deep reinforcement learning approach to manage large queues efficiently.
result MERLIN outperforms existing methods by a large margin (>22%) on multiple queue sizes.
Unified framework for efficient surrogate modeling in manufacturing.
problem Large data requirements and heterogeneous data sources in manufacturing.
method Hierarchical multi-task multi-fidelity (H-MT-MF) framework for Gaussian process-based surrogate modeling.
result Improves prediction accuracy by up to 23% compared to existing methods.
RL applied to finance tasks, highlighting challenges and future directions.
problem Decision-making tasks in finance using RL.
method Meta-analysis of RL applications, identifying challenges and proposing future directions.
result Challenges in RL performance and future research directions.
ARML learns task relations to improve meta-learning efficiency.
problem Handling task heterogeneity in meta-learning.
method Automatically extracts cross-task relations and constructs a meta-knowledge graph.
result ARML outperforms state-of-the-art baselines in few-shot learning tasks.
This paper won 1st place in forecasting and investment challenges, improving on meta-learning and parametric models.
problem Forecasting and investment challenges in time-series data.
method Hypernetworks and adversarial portfolios to design time-series models.
result Outperformed state-of-the-art meta-learning methods and conventional parametric models.
New neural network boosts authorship verification on social media.
problem Challenges in verifying authorship of short, diverse social media messages.
method Proposes a new neural network topology for similarity learning.
result Significantly improved performance on author verification tasks.
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…