Research
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.

168,657 papers · 148 categories

Trend · papers per month

2945888811,175 · Jun 202019922001200920172026
48 results for training task diversity

Training task diversity improves ICL with linear attention.

problem Understanding the impact of training task diversity on in-context learning.
method Modeling training task vectors as a mixture of low-rank Gaussians.
result Our model explains why training with task diversity shortens the ICL plateau and achieves out-of-distribution generalization.

Proposes Ada-Sit method for mortality prediction of rare diseases.

problem Data insufficiency and clinical diversity of rare diseases make mortality prediction hard.
method Initialization-sharing multi-task learning method (Ada-Sit) for fast adaptation to similar tasks.
result Experimental results show the proposed model is effective for mortality prediction of diverse rare diseases.

DEN learns diverse tasks to generalize to unseen tasks.

problem Generalization from a diverse set of classification tasks with limited data.
method Three-block architecture: covariate transformation, distribution embedding, and classification.
result DEN outperforms existing methods in various synthetic and real tasks.

New analysis shows diverse classes in pre-training boost NLP performance.

problem Improving sample efficiency in downstream NLP tasks.
method Proved that diverse classes in pre-training lead to better performance, using a large last linear layer singular value.
result Transfer learning excess risk improves with large ildeν ildeν and $O\left(\frac{1}{ ildeν \sqrt{n}} ight)$ rate.

This work studies the impact of intra-/inter-class diversity on pre-training datasets and finds a balance for optimal performance.

problem The impact of intra-/inter-class diversity on supervised pre-training datasets and their effect on downstream tasks.
method Empirical study and theoretical analysis of the relationship between diversity types and downstream performance.
result The optimal class-to-sample ratio is invariant to the size of the pre-training dataset and can be predicted.

DIVA generates diverse tasks for complex simulators, enabling adaptive agent training.

problem Lack of diverse training data for complex, open-ended simulators.
method Evolutionary approach using domain randomization and procedural generation.
result Successfully trains adaptive agent behavior in complex simulators.

Ensembles depend on diversity for improved performance. Many ensemble training methods, therefore, attempt to optimize for diversity, which they almost always define in terms of differences in training set predictions. In this paper, however, we demonstrate the diversity of predictions on the training set does not nece…

2019-11-04abs ↗pdf ↗

Proposes a Bayesian federated learning method for diverse tasks.

problem Current federated learning approaches focus on homogeneous tasks, ignoring task diversity.
method Integrates multi-task learning with MOGP at the local level and federated learning at the global level.
result Demonstrates superior predictive performance and uncertainty calibration on diverse tasks.

This paper improves ensemble learning for vision tasks by encouraging diversity in predictions.

problem Generating effective ensembles of neural networks for multi-modal data.
method Explicitly optimize a diversity inducing adversarial loss for learning stochastic latent variables.
result Significant improvements in classification accuracy and out-of-distribution detection compared to baselines.

Improved transfer learning with expert models, reducing compute and speeding up performance.

problem Improving sample efficiency and reducing computational requirements for new tasks.
method Training a diverse set of experts using existing label structures and performance proxies to select the relevant expert for each target task.
result Significant speed-up of 2-3 orders of magnitude compared to competing approaches.

The study provides precise asymptotic theory for in-context learning by Transformers.

problem Understanding the sample complexity, pretraining task diversity, and context length for successful in-context learning.
method An exactly solvable model of linear regression task by linear attention, deriving sharp asymptotics.
result Double-descent learning curve with increasing pretraining examples, phase transition between low and high task diversity regimes.

This paper shows how diverse tasks can make inefficient exploration in MTRL efficient.

problem The challenge of efficient exploration in Multitask Reinforcement Learning.
method A generic policy-sharing algorithm with myopic exploration design trained on diverse tasks.
result A generic policy-sharing algorithm with myopic exploration design can be sample-efficient in MTRL.

aMCL uses annealing to improve hypothesis diversity in ambiguous tasks.

problem Limitations of Winner-takes-all in predicting plausible hypotheses.
method Combines simulated annealing with Multiple Choice Learning (MCL).
result Enhanced exploration of hypothesis space during training.

Study on neural scaling laws for solving linear systems in-context.

problem Theoretical guarantees for solving linear systems using a linear transformer architecture.
method Neural scaling laws and task diversity for in-domain and out-of-domain generalization.
result Novel notion of task diversity for necessary and sufficient condition of generalization under task shifts.

Transformers learn to generalize out-of-distribution with diverse pretraining tasks.

problem Conditions for pretrained transformers to generalize out-of-distribution.
method Empirical study of task diversity and pretraining distribution.
result As task diversity increases, transformers transition from specialized to generalized solutions.

Proposes a new curriculum learning approach to improve deep RL agent generalization.

problem Challenges in training deep RL agents to generalize over unseen situations.
method Two-stage curriculum learning approach: teacher learns high-exploration curriculum, distills priors to generate expert curriculum.
result 50% improvement in average performance over state-of-the-art methods.

Improved RL training for DMs reduces mode collapse and preserves diversity.

problem Mode collapse and training instability in RL fine-tuned diffusion models.
method Dynamic hierarchical RL training with sliding-window parameter regularisation.
result Models trained with HRF achieve better preservation of diversity in downstream tasks.

MetaPerturb learns to improve generalization across different tasks and architectures.

problem Improving generalization on unseen data for diverse tasks and architectures.
method MetaPerturb is a meta-learned set-based perturbation function that improves generalization performance across heterogeneous tasks and architectures.
result MetaPerturb significantly outperforms baselines on most tasks and architectures with minimal increase in parameter size and no hyperparameters to tune.

New method learns diverse solutions in reinforcement learning without gradient bias.

problem Lack of diverse solutions in reinforcement learning tasks.
method Maximizes state-action-based mutual information directly, using variational lower bound.
result Successfully learns an infinite set of diverse solutions.

DiCE uses diverse agents to explore and learn, avoiding local minima.

problem Local minima in RL due to limited exploration and correlated behavior.
method DiCE employs a group of heterogeneous agents to explore simultaneously and share experiences, with a diversity regularization mechanism.
result DiCE achieves substantial improvement over baselines in MuJoCo locomotion tasks.

Meta-CoTGAN improves adversarial text generation by preventing mode collapse.

problem Mode collapse in adversarial text generation.
method Meta-Cooperative Training Paradigm with a language model.
result Meta-CoTGAN effectively slows down mode collapse and improves generation quality and diversity.

Meta-learning techniques like MAML and Reptile fail to generalize well to out-of-distribution tasks compared to simple finetuning.

problem Generalization of meta-learning techniques in low-data scenarios.
method Investigation of MAML, Reptile, and finetuning on various tasks.
result MAML and Reptile specialize for fast adaptation but fail to generalize to out-of-distribution tasks.

Few-shot Learning aims to learn classifiers for new classes with only a few training examples per class. Existing meta-learning or metric-learning based few-shot learning approaches are limited in handling diverse domains with various number of labels. The meta-learning approaches train a meta learner to predict weight…

2019-01-26abs ↗pdf ↗

PDTS improves robustness in sequential decision-making.

problem Robust active task sampling for efficient and reliable decision-making.
method Characterizes robust active task sampling as a Markov decision process, proposes PDTS method.
result Significantly improves zero-shot and few-shot adaptation robustness.

We propose MAD-GAN, an intuitive generalization to the Generative Adversarial Networks (GANs) and its conditional variants to address the well known problem of mode collapse. First, MAD-GAN is a multi-agent GAN architecture incorporating multiple generators and one discriminator. Second, to enforce that different gener…

2017-04-10abs ↗pdf ↗

Neural networks extrapolate poorly in simple tasks but succeed in complex ones.

problem Understanding neural networks' extrapolation capabilities and conditions for success.
method Analyzing ReLU MLPs and GNNs, connecting to neural tangent kernel.
result ReLU MLPs learn linear functions but not most nonlinear ones, while GNNs succeed in complex tasks due to task-specific non-linearities.

Model-agnostic meta-learners aim to acquire meta-learned parameters from similar tasks to adapt to novel tasks from the same distribution with few gradient updates. With the flexibility in the choice of models, those frameworks demonstrate appealing performance on a variety of domains such as few-shot image classificat…

2019-10-30abs ↗pdf ↗

DivDis learns diverse hypotheses from underspecified data to improve robustness.

problem Learning from underspecified datasets leads to multiple equally viable solutions, causing out-of-distribution issues.
method DivDis framework: 1) learns diverse hypotheses using unlabeled test data, 2) selects one hypothesis with minimal additional supervision.
result DivDis finds robust features in image and natural language processing problems.

Ensemble learning is a very prevalent method employed in machine learning. The relative success of ensemble methods is attributed to their ability to tackle a wide range of instances and complex problems that require different low-level approaches. However, ensemble methods are relatively less popular in reinforcement …

2020-01-15abs ↗pdf ↗

The paper improves QD policy ensembles using distribution ratio estimators.

problem Training diverse and high-quality reinforcement learning agents.
method Using Stein variational gradient descent and distribution ratio estimators.
result The method generates diverse and high-quality reinforcement learning agents.

The two key players in Generative Adversarial Networks (GANs), the discriminator and generator, are usually parameterized as deep neural networks (DNNs). On many generative tasks, GANs achieve state-of-the-art performance but are often unstable to train and sometimes miss modes. A typical failure mode is the collapse o…

2019-01-30abs ↗pdf ↗