Can we use deep learning to predict when deep learning works? Our results suggest the affirmative. We created a dataset by training 13,500 neural networks with different architectures, on different variations of spiral datasets, and using different optimization parameters. We used this dataset to train task-independent…
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
48 results for “task-independent optimization”
We present a framework for autonomously learning a portable representation that describes a collection of low-level continuous environments. We show that these abstract representations can be learned in a task-independent egocentric space specific to the agent that, when grounded with problem-specific information, are …
New framework for task-independent legged locomotion.
problem Building stable legged locomotion systems in robotics.
method Task-independent spiking central pattern generator using learning methods.
result Robotic legged locomotion at different speeds and within the same gait cycle.
SRPO improves AI alignment with human preferences through self-improvement and task-independent optimization.
problem AI models trained with RLHF lack self-correction mechanisms and struggle with task generalization.
method SRPO formulates the preference learning problem as a min-max objective, optimizing a self-improvement policy and a generative policy in an adversarial fashion, making the solution task-independent.
result SRPO outperforms existing methods, achieving 90% AI Win-Rate on XSum and 56% on Arena-Hard prompts after a single revision.
Learning powerful data embeddings has become a center piece in machine learning, especially in natural language processing and computer vision domains. The crux of these embeddings is that they are pretrained on huge corpus of data in a unsupervised fashion, sometimes aided with transfer learning. However currently in …
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.
The paper analyzes the performance of delay-based reservoir computing using eigenvalue analysis.
problem Quantifying the performance of delay-based reservoir computing.
method Eigenvalue analysis of the dynamical system to predict reservoir computing performance.
result The performance of a reservoir computing system can be predicted by analyzing the small signal response and eigenvalue spectrum.
TIPRDC anonymizes data features to protect privacy while retaining useful information.
problem Privacy concerns from crowdsourced data hinder deep learning applications.
method Hybrid training method combining adversarial and mutual information estimation.
result Feature extractor hides private information while preserving original data features.
While deep learning and deep reinforcement learning (RL) systems have demonstrated impressive results in domains such as image classification, game playing, and robotic control, data efficiency remains a major challenge. Multi-task learning has emerged as a promising approach for sharing structure across multiple tasks…
We compute the transition probability between two learning tasks, and show that it decomposes into two factors. The first depends on the geometry of the loss landscape of a model trained on each task, independent of any particular model used. This is related to an information theoretic distance function, but is insuffi…
Pre-trained language model boosts RL efficiency.
problem Low sample efficiency in RL, especially in lifelong learning.
method Use a pre-trained task-independent language model for transfer learning.
result Goal-conditional RL agents become more sample efficient.
The task of representing entire graphs has seen a surge of prominent results, mainly due to learning convolutional neural networks (CNNs) on graph-structured data. While CNNs demonstrate state-of-the-art performance in graph classification task, such methods are supervised and therefore steer away from the original pro…
Exploration is a difficult challenge in reinforcement learning and even recent state-of-the art curiosity-based methods rely on the simple epsilon-greedy strategy to generate novelty. We argue that pure random walks do not succeed to properly expand the exploration area in most environments and propose to replace singl…
Learning Model Biascs.LG
In this paper the problem of {\em learning} appropriate domain-specific bias is addressed. It is shown that this can be achieved by learning many related tasks from the same domain, and a theorem is given bounding the number tasks that must be learnt. A corollary of the theorem is that if the tasks are known to possess…
Learning representations with diversified information remains as an open problem. Towards learning diversified representations, a new approach, termed Information Competing Process (ICP), is proposed in this paper. Aiming to enrich the information carried by feature representations, ICP separates a representation into …
Magnetoencephalography and electroencephalography (M/EEG) are non-invasive modalities that measure the weak electromagnetic fields generated by neural activity. Estimating the location and magnitude of the current sources that generated these electromagnetic fields is a challenging ill-posed regression problem known as…
New method clusters multimodal data with consistency.
problem Multimodal clustering with unaligned data.
method Conjugate mixture models and EM algorithm.
result Consistent multimodal clustering achieved.
A great variety of text tasks such as topic or spam identification, user profiling, and sentiment analysis can be posed as a supervised learning problem and tackle using a text classifier. A text classifier consists of several subprocesses, some of them are general enough to be applied to any supervised learning proble…
Many machine learning techniques have been proposed in the last few years to process data represented in graph-structured form. Graphs can be used to model several scenarios, from molecules and materials to RNA secondary structures. Several kernel functions have been defined on graphs that coupled with kernelized learn…
The paper proposes reusable network components by making them compatible across tasks.
problem Training networks for different tasks independently leads to incompatible components.
method The paper splits a network into a features extractor and a target task head, and proposes various approaches to make them compatible.
result The proposed methods produce components that are directly compatible without compromising accuracy on original tasks.
Multi-task/Multi-output learning seeks to exploit correlation among tasks to enhance performance over learning or solving each task independently. In this paper, we investigate this problem in the context of Gaussian Processes (GPs) and propose a new model which learns a mixture of latent processes by decomposing the c…
Task-oriented dialog presents a difficult challenge encompassing multiple problems including multi-turn language understanding and generation, knowledge retrieval and reasoning, and action prediction. Modern dialog systems typically begin by converting conversation history to a symbolic object referred to as belief sta…
L2M learns to match distributions for domain adaptation without relying on hand-crafted priors.
problem Difficult to directly match cross-domain distributions; existing methods fail to uncover underlying relationships.
method Learning to Match (L2M) framework that learns distribution matching loss using a meta-network in a data-driven way.
result L2M outperforms state-of-the-art methods on public datasets and transfers from pneumonia to COVID-19 images.
Auxiliary Tuning adapts pre-trained models for novel tasks efficiently.
problem Adapting pre-trained models for new tasks efficiently.
method Supplementing pre-trained model with an auxiliary model that shifts output distribution.
result Achieved similar results to training from scratch with fewer resources.
Mining tasks over sequential data, such as clickstreams and gene sequences, require a careful design of embeddings usable by learning algorithms. Recent research in feature learning has been extended to sequential data, where each instance consists of a sequence of heterogeneous items with a variable length. However, m…
AI bias arises from human-defined goals, not algorithmic flaws.
problem AI bias due to human-defined goals in LLMs.
method Purpose-conditioned cognition and revealing downstream use of LLM outputs.
result AI bias can be reduced by purpose-aware prompting but not fully by regularization.
Multi-task learning (MTL) is a supervised learning paradigm in which the prediction models for several related tasks are learned jointly to achieve better generalization performance. When there are only a few training examples per task, MTL considerably outperforms the traditional Single task learning (STL) in terms of…
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…
Study finds multi-task learning and pre-training can improve healthcare models on EHR data.
problem Improving model performance on diverse EHR tasks using multi-task learning.
method Examined multi-task learning across various EHR tasks and training schemes, using pre-training and fine-tuning.
result Significant gains in model performance achieved via multi-task pre-training and single-task fine-tuning.
Speech datasets for identifying Alzheimer's disease (AD) are generally restricted to participants performing a single task, e.g. describing an image shown to them. As a result, models trained on linguistic features derived from such datasets may not be generalizable across tasks. Building on prior work demonstrating th…
Prediction tasks over nodes and edges in networks require careful effort in engineering features used by learning algorithms. Recent research in the broader field of representation learning has led to significant progress in automating prediction by learning the features themselves. However, present feature learning ap…
Many efforts have been devoted to training generative latent variable models with autoregressive decoders, such as recurrent neural networks (RNN). Stochastic recurrent models have been successful in capturing the variability observed in natural sequential data such as speech. We unify successful ideas from recently pr…
Study multi-task learning with low-rank representation in stochastic linear bandits.
problem Transfer learning across multiple linear bandit tasks with shared low-dimensional representation.
method Proposes a greedy policy with trace norm regularization to implicitly learn a low-rank representation without knowing the rank.
result Upper bound on multi-task regret of , showing benefit over independent task solving.
Autonomous agents situated in real-world environments must be able to master large repertoires of skills. While a single short skill can be learned quickly, it would be impractical to learn every task independently. Instead, the agent should share knowledge across behaviors such that each task can be learned efficientl…
Attributed network embedding has attracted plenty of interest in recent years. It aims to learn task-independent, low-dimensional, and continuous vectors for nodes preserving both topology and attribute information. Most of the existing methods, such as random-walk based methods and GCNs, mainly focus on the local info…
MTNPs jointly model multiple correlated tasks from various sources.
problem Naive NPs can only model a single stochastic process and infer tasks independently.
method MTNPs are a hierarchical extension of NPs that jointly infer tasks from multiple stochastic processes, considering inter-task correlation and handling incomplete data.
result MTNPs successfully model multiple tasks jointly, discovering and exploiting their correlations in various real-world data.
Despite a multitude of empirical studies, little consensus exists on whether neural networks are able to generalise compositionally, a controversy that, in part, stems from a lack of agreement about what it means for a neural model to be compositional. As a response to this controversy, we present a set of tests that p…
The paper extends IPC framework to stationary physical systems and validates it with a photonic system.
problem Characterizing the computational capabilities of stationary physical systems in a principled, data-efficient way.
method Extended IPC framework, established fundamental results, derived asymptotic bias, introduced data-efficient estimation methods.
result IPC strongly correlates with machine-learning performance and provides a reliable estimate of system dimensionality.
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.
PPI uses proxy data to improve inference from limited labels across related tasks.
problem Statistical inference with limited labels across multiple related tasks.
method Prediction-powered inference framework that uses cross-task recalibration to improve power and accuracy.
result Cross-task recalibration can substantially reduce confidence interval widths when labels are scarce.
FSN model improves few-shot learning by generalizing to new tasks.
problem Few-shot learning struggles with tasks outside its training domain.
method FSN uses topology-inspired approach to model classes flexibly.
result FSN outperforms state-of-the-art models on new tasks.
A new metric FRD improves comparing medical images.
problem Comparing medical images for distribution or domain differences.
method Developed a new metric FRD using standardized radiomic features.
result FRD outperforms other metrics in various medical imaging applications.
Low Rank for Rank: Uncertainty-Aware Task-Specific LLM Ranking under Sparse Pairwise Comparisonsstat.ME
Low-rank framework for task-specific LLM ranking from sparse comparisons.
problem Challenges in reliable task-specific ranking of LLMs under sparse, imbalanced comparisons.
method Low-rank modeling of task-by-model ability matrix, max-norm accurate estimator, task-wise top-K recovery guarantees, uncertainty quantification framework.
result Improves sample efficiency and produces tighter, better-calibrated ranking certificates.
Unified principle LZN unifies generative modeling, representation learning, and classification.
problem Disjoint solutions for generative modeling, representation learning, and classification.
method LZN creates a shared latent space for all tasks, using encoders and decoders for each data type.
result LZN improves FID on CIFAR10 and outperforms existing methods in representation learning and joint generation/classification.
An efficient application of Bayesian optimization to an industrial MDO framework for aircraft designcs.CE
Bayesian optimization reduces computational effort in aircraft design optimization.
problem High computational cost in industrial aircraft design optimization.
method Constrained Bayesian optimization (Super Efficient Global Optimization with Mixture of Experts)
result Significant computational efficiency improvements over existing Isight optimizers.
Bayesian optimization method tackles combinatorial spaces, scalable for large data.
problem Optimization over combinatorial categorical spaces in natural sciences.
method Combines variational optimization and continuous relaxations for gradient-based optimization.
result Method performs comparably to state-of-the-art methods while scaling well.
New algorithm solves complex stopping problems with robust optimization.
problem Solving complex stochastic optimal stopping problems.
method Simulation-based robust optimization with exact reformulation as a zero-one bilinear program.
result Developed polynomial-time heuristics and algorithms for practical solution.
L2O uses ML to optimize traditional optimization techniques.
problem Real-world optimization problems with shared structures.
method Exploiting shared structures to enhance optimization techniques.
result Better or faster solutions through machine learning integration.