Study selective classification with limited feedback in online learning.
problem Resource-limited and safety-critical domains where feedback is only received on abstentions.
method Versioning-based schemes for minimizing mistakes and abstentions.
result Constructed schemes that make few mistakes and minimal excess abstentions.
The paper introduces reservoir computing models for complex systems.
problem Modeling complex engineering systems using nonlinear autoregression.
method Introduces reservoir computing with output feedback as stationary and ergodic infinite-order nonlinear autoregressive models.
result Demonstrates versatility of classical and quantum reservoir computers in modeling synthetic and real data.
Testing the implementation of deep learning systems and their training routines is crucial to maintain a reliable code base. Modern software development employs processes, such as Continuous Integration, in which changes to the software are frequently integrated and tested. However, testing the training routines requir…
LATM framework uses LLMs to create and reuse tools for efficient problem-solving.
problem Improving problem-solving capabilities of LLMs with external tools.
method Closed-loop framework with two phases: tool making and tool using. LLMs act as both tool makers and users. Resource-intensive model for tool making, lightweight model for tool using.
result LATM framework achieves performance equivalent to using a powerful LLM for both roles but with significantly reduced costs.
Neural Architecture Search has shown potential to automate the design of neural networks. Deep Reinforcement Learning based agents can learn complex architectural patterns, as well as explore a vast and compositional search space. On the other hand, evolutionary algorithms offer higher sample efficiency, which is criti…
Research on neural networks has gained significant momentum over the past few years. Because training is a resource-intensive process and training data cannot always be made available to everyone, there has been a trend to reuse pre-trained neural networks. As such, neural networks themselves have become research data.…
Paper speeds up large foundation models for time series data.
problem Resource-intensive foundation models limit accessibility.
method Dimensionality reduction techniques, including PCA and neural network adapters.
result Up to 10x speedup and 4.5x more datasets fit on a single GPU.
Real-time uncertainty estimation for computer vision tasks.
problem Real-time inference of uncertainty in deep learning models.
method Uncertainty-Aware Distribution Distillation method for fast inference.
result Significantly reduced inference time with improved uncertainty and predictive performance.
A new deep learning method using Boolean logic reduces training and inference energy.
problem High computational and energy costs in deep learning training and inference.
method Introduces Boolean weights and inputs for efficient training using Boolean logic.
result Achieves full-precision accuracy in ImageNet classification and surpasses state-of-the-art results in semantic segmentation.
Machine learning methods have recently achieved high-performance in biomedical text analysis. However, a major bottleneck in the widespread application of these methods is obtaining the required large amounts of annotated training data, which is resource intensive and time consuming. Recent progress in self-supervised …
In many learning situations, resources at inference time are significantly more constrained than resources at training time. This paper studies a general paradigm, called Differentiable ARchitecture Compression (DARC), that combines model compression and architecture search to learn models that are resource-efficient a…
Accurately predicting patients' risk of 30-day hospital readmission would enable hospitals to efficiently allocate resource-intensive interventions. We develop a new method, Categorical Co-Frequency Analysis (CoFA), for clustering diagnosis codes from the International Classification of Diseases (ICD) according to the …
Risk control improves EENNs to make faster predictions without sacrificing accuracy.
problem Determining safe times for EENNs to exit early without degrading performance.
method Adapting risk control frameworks to EENNs to tune their exiting mechanism.
result Risk control enables EENNs to make faster predictions while maintaining user-specified performance goals.
Post-training corrections boost time-series forecasting accuracy.
problem Improving forecasting accuracy of large models after training.
method Sequential application of carefully selected corrections to predictions.
result Up to 30% improvement in forecasting accuracy with minimal overhead.
Diffusion LLMs can efficiently generate harmful prompts for adversarial testing.
problem Generating harmful prompts for adversarial testing is resource-intensive and costly.
method Transformed adversarial prompt optimization into an efficient inference task using pretrained Diffusion LLMs.
result Only a few conditional samples are required to generate harmful prompts with high reward.
A new method reduces communication costs in decentralized optimization.
problem Decentralized optimization with non-convex cost functions.
method LU-GT method with local updates.
result LU-GT achieves the same communication complexity as Federated Learning and maintains solution quality.
State-of-the-art convolutional neural networks (CNNs) used in vision applications have large models with numerous weights. Training these models is very compute- and memory-resource intensive. Much research has been done on pruning or compressing these models to reduce the cost of inference, but little work has address…
A new framework for controllable generation of discrete masked models.
problem Efficient controllable generation of discrete data models.
method Plug-and-play framework based on importance sampling.
result Demonstrates versatility across multiple domains, including protein design.
LEMON uses pre-trained models to scale neural networks efficiently.
problem Efficiency in scaling deep neural networks, especially Transformers, which are resource-intensive to train from scratch.
method LEMON initializes scaled models using pre-trained weights and optimizes learning rates.
result Significant reduction in training time and computational costs for Vision Transformers and BERT.
BOAT optimizes multiple antibody properties efficiently.
problem Balancing multiple drug-like properties in antibody design.
method Bayesian optimization framework coupling surrogate modeling and genetic algorithm.
result Competitive performance with state-of-the-art multi-objective protein optimization methods.
Optimizes CNN architectures by analyzing receptive fields without training.
problem CNNs often have too many layers, making them resource-intensive and less effective.
method Layer-wise analysis of receptive fields to identify unproductive layers.
result Identifies and removes unproductive layers, improving CNN performance and efficiency.
The paper proposes a method to find subgroups with significant treatment effects in noisy data.
problem Estimating the causal effects of interventions on noisy outcomes.
method A machine-learning method specifically optimized for finding subgroups with significant effects, designed to maximize the probability of obtaining a statistically significant positive treatment effect.
result The proposed method yields higher power in detecting subgroups affected by the treatment compared to standard tree-based tools.
A new method optimizes complex engineering designs under uncertainty efficiently.
problem Optimizing large, uncertain engineering designs with limited resources.
method Multi-level informed optimization via decomposed Kriging.
result Significantly faster and more accurate optimization compared to state-of-the-art methods.
Formalizes weak and strong verification for LLMs, controlling errors without assumptions.
problem Balancing cost and reliability in reasoning with LLMs.
method Formalizes weak-strong verification policies, introduces metrics, develops online algorithm.
result Optimal policies admit a two-threshold structure, and calibration and sharpness govern value of weak verifiers.
ProEval efficiently estimates AI performance and discovers failures using pre-trained Gaussian Processes.
problem Resource-intensive evaluation of generative AI models.
method ProEval uses pre-trained Gaussian Processes and Bayesian quadrature to estimate performance and discover failures.
result ProEval requires significantly fewer samples to achieve accurate performance estimates and reveals more diverse failure cases.
New methods improve inference with scarce labels using regression.
problem Efficient inference with limited labeled data.
method Relates PPI++ to ordinary least squares regression and uses robust regressors.
result Improved variance in estimators for few-label scenarios.
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…
A method selects candidates based on predictions with statistical control.
problem Screening candidates for resource-intensive steps like hiring or drug discovery.
method Wraps around any prediction model to produce a subset of candidates with controlled false selection rate.
result Empirically demonstrates selection of candidates whose predictions exceed a data-dependent threshold.
Study optimizes GCS operations with deep learning and reinforcement learning.
problem Maximizing storage performance in GCS with resource-efficient simulations.
method Introduces MLD model for fast flow prediction and well control optimization, combining deep learning and reinforcement learning.
result Achieves highest NPV while reducing computational resources by over 60%.
Framework extracts symptoms from EHRs for rapid disease outbreak detection.
problem Extracting relevant data from unstructured medical texts.
method Conformal active learning for efficient data mining.
result Framework achieves strong performance with minimal manual labeling.
EORM boosts LLM accuracy with a lightweight, energy-based verifier.
problem Efficiently verifying mathematical reasoning in large language models.
method Energy-based framework to rank Chain-of-Thought solutions using simple outcome labels.
result EORM boosts LLM accuracy to 90.7% on GSM8k and 63.7% on MATH with only 55M parameters.
AdaScale SGD adapts learning rates for large-batch training efficiently.
problem Adapting learning rates for large-batch training to balance speed-ups and model quality.
method Adaptive learning rate adaptation based on gradient variance.
result AdaScale achieves reliable speed-ups for a wide range of batch sizes without degrading model quality.
State-of-the-art image recognition systems use sophisticated Convolutional Neural Networks (CNNs) that are designed and trained to identify numerous object classes. Such networks are fairly resource intensive to compute, prohibiting their deployment on resource-constrained embedded platforms. On one hand, the ability t…
New algorithm improves stability of optimization algorithms by adapting step-size.
problem Optimization algorithms' effectiveness is sensitive to step-size hyperparameters.
method Adapts NGN step-size method with momentum to enhance stability.
result Achieves convergence rate of O(1/√K) without restrictive assumptions.
Finite resources limit false discovery rate control in structured hypothesis spaces.
problem Controlling false discovery rate in hypothesis testing with finite data and structured hypothesis spaces.
method Framework for exact FDR control and adaptive power maximization.
result Exact FDR control and adaptive power maximization.
Unified framework for scalable black-box optimization.
problem Expensive black-box evaluations in scientific and engineering domains.
method Integrates active learning, multi-armed bandits, and distributed computing.
result Consistently outperforms state-of-the-art black-box optimizers.
New CycleGAN uses invertible generator for faster, less resource-intensive CT denoising.
problem Efficient unsupervised CT denoising without paired data.
method Single generator with wavelet residual domain, no discriminators, cycle consistency via invertible generator.
result Significantly improved denoising performance with faster training and less parameters.
Sleep stage classification constitutes an important element of sleep disorder diagnosis. It relies on the visual inspection of polysomnography records by trained sleep technologists. Automated approaches have been designed to alleviate this resource-intensive task. However, such approaches are usually compared to a sin…
Method constructs finance LLMs without instruction data using pretraining and model merging.
problem Developing domain-specific LLMs for finance is resource-intensive.
method Continual pretraining on financial data + model merging of instruction-tuned and domain-specific pretrained vectors.
result Successfully constructs instruction-tuned LLMs for finance without additional instruction data.
G-CREWE efficiently aligns large networks using node embeddings and compression.
problem Efficiently aligning large networks for various applications.
method Uses node embeddings and compression to align networks at fine and coarse resolutions.
result G-CREWE achieves efficient and accurate network alignment, twice as fast as existing methods.
Improved inference efficiency for complex simulations.
problem Challenges in performing inference under resource-intensive stochastic simulators.
method Active sequential neural posterior estimation (ASNPE) integrating active learning into posterior estimation.
result Improved sample efficiency with low computational overhead.
A framework for modular training of robust generative models.
problem Training large generative models is resource-intensive and requires heuristic tuning.
method Modular training using a gating mechanism and a minimax game to find a robust gate.
result The modular approach can theoretically outperform monolithic baselines and is scalable.
Efficiently generates high-resolution images with reduced sampling time using LEGO bricks.
problem Efficiently generating high-resolution images with reduced sampling time.
method Introduces LEGO bricks that integrate Local-feature Enrichment and Global-content Orchestration to create a test-time reconfigurable diffusion backbone.
result Significantly reduces sampling time compared to other methods.
Efficient RL method uses SSL for small labeled data in health outcomes.
problem Lack of precise health outcome data for reinforcement learning.
method Semi-supervised learning approach for Q-learning and value estimation.
result Method efficiently estimates Q-function and value function, robust to mis-specification.
New method shows how order of gradient updates impacts stability and convergence in deep learning.
problem Training deep learning models can be unstable and computationally expensive.
method Theoretical analysis and experiments with backward-SGD.
result The order of gradient updates affects stability and convergence, leading to improved performance.
CAMS selects best pre-trained model for unlabeled data points.
problem Efficiently utilizing pre-trained models and unlabeled data.
method Contextual active model selection algorithm with two components: contextual model selection and active query.
result CAMS requires less than 10% labeling effort compared to existing methods, achieving similar or better accuracy.
A new overlapping space solves the configuration search problem for graph embeddings.
problem Configuring product spaces for graph embeddings is resource-intensive and impractical.
method Introducing overlapping spaces that share subsets of coordinates between different types of spaces (Euclidean, hyperbolic, spherical).
result Overlapping spaces achieve nearly optimal results without configuration tuning, reducing training time.
Classification-as-a-Service (CaaS) is widely deployed today in machine intelligence stacks for a vastly diverse set of applications including anything from medical prognosis to computer vision tasks to natural language processing to identity fraud detection. The computing power required for training complex models on l…