Reducing ICD-10 code granularity improves cost model accuracy and stability.
problem High-dimensional regression with ICD-10 codes leads to unstable coefficient estimates.
method Log-linear analytics approach to cost model regularization through diagnostic code merging.
result Reducing ICD-10 code granularity from 7 characters to 6 or fewer improves model interpretability and consistency.
A simpler cost-sensitive encoding method improves multi-label classification performance.
problem Cost-sensitive multi-label classification challenges.
method Cost-sensitive reference pair encoding (CSRPE) with cluster-based encoding, weight-based training, and voting-based decoding.
result CSRPE outperforms state-of-the-art algorithms across various MLC criteria.
CCA features from medical codes predict future surgeries.
problem Predicting future surgeries based on medical codes.
method Canonical correlation analysis applied to sequences of medical codes.
result CCA embeddings capture meaningful relationships among medical codes.
ICQ improves high-dimensional similarity search without sacrificing precision.
problem High-dimensional similarity search is computationally expensive.
method Interleaved Composite Quantization (ICQ) reduces code length and quantization error.
result ICQ achieves fast similarity search without using shorter codes.
Deep neural network predicts health costs better than traditional models.
problem Accurate prediction of healthcare costs for optimal cost management.
method Developed a deep neural network to predict future health care costs from health insurance claims records.
result Deep neural network outperformed ridge regression and Morbi-RSA models in cost prediction.
Two new coding schemes improve the efficient communication of noisy data.
problem Efficient communication of noisy data in machine learning.
method Ordered Random Coding (ORC) and Hybrid Coding Scheme.
result Improved coding schemes over existing approaches.
A new hashing framework learns multiple hash codes for each image to improve hash bucket search efficiency.
problem Existing hashing methods fail to handle complex image retrieval scenarios efficiently.
method Multiple Code Hashing (MCH) framework with deep reinforcement learning.
result Significant improvement in hash bucket search performance compared to single-code methods.
Poisson variational autoencoders introduce a metabolic cost term that penalizes high baseline activity.
problem Energy constraints in computation.
method Poisson variational autoencoders with a Kullback-Leibler divergence term proportional to firing rates.
result Poisson variational autoencoders introduce a metabolic cost term that penalizes high baseline activity.
Graph-Structured Cache improves code completion and variable naming tasks.
problem Learning open vocabulary in source code.
method Graph-Structured Cache for handling new words in code.
result Improves code completion and variable naming tasks by over 100%.
Paper improves MIRACLE for faster, more robust neural network compression.
problem Efficiently compressing neural networks while maintaining performance.
method Introduces Mean-KL parameterization to constrain compression cost.
result Mean-KL parameterization leads to twice as fast convergence and more robust compression.
Paper proposes a VB method for TS-SBP mixture models with reduced computational cost.
problem Efficiently learning tree-structured stick-breaking process mixture models.
method Utilizes Bayes coding algorithm for context tree models to calculate sums over all possible trees.
result Proposes a learning algorithm with less computational cost for TS-SBP mixture of Gaussians.
Paper optimizes distributed learning by reducing gradient computation time.
problem Efficiently compute gradients in distributed learning tasks.
method Recursive polynomial constructions for coding across data subsets and vector components.
result Optimal tradeoff between computation load, straggler tolerance, and communication cost achieved.
AI agent predicts industry and product/service codes for companies.
problem Manual curation of company data is expensive and prone to errors.
method Hierarchical multi-class industry code classifier with multi-label product/service code classifier.
result High accuracy (92-96%) achieved with limited labeled data.
New bounds on nearly maximally predictive features help improve data prediction.
problem Inferring maximally predictive features from data sets is often uncountably infinite.
method Derived upper-bounds on the number and coding cost of nearly maximally predictive features.
result Mixed-state predictive features offer a substantial improvement over finite-order Markov models.
This paper speeds up simulations of hypersonic reentry by combining traditional and neural methods.
problem Accurately simulating hypersonic reentry with chemical reactions is computationally expensive.
method A hybrid simulation code combining a traditional fluid dynamics solver with a neural network approximating chemical reactions.
result Achieved significant acceleration factors (imes10 to imes18.6) while maintaining accuracy. New method extracts stock returns from alphas without combining them, saving costs.
problem Costly alpha combos in hedge funds.
method Explicit algorithm and source code for extracting expected returns from alphas.
result Substantial cost savings (3% vs 10%) and avoidance of noise.
A deep learning algorithm designs low-cost SPP films.
problem Designing SPP films with high accuracy and low cost.
method Guided deep learning algorithm with low-cost sample replacement.
result Deep CNN learns to replace precious metals with ordinary metals, reducing cost.
Paper proposes efficient communication scheme for statistical learning.
problem Efficiently conveying a statistical hypothesis from a client to a server.
method Joint training and source coding scheme with KL divergence constraints.
result Guarantees small average empirical risk, generalization error, and communication cost.
New algorithm for active learning from feedback coding.
problem Efficiently selecting examples for labeling in active machine learning.
method Formalized structural similarities between active learning and feedback channel coding, developed an optimal transport-based algorithm called Approximate Posterior Matching (APM).
result Learning performance comparable to existing methods at reduced computational cost.
New method clusters health codes for better risk adjustment.
problem Improving insurer incentives to attract lower-cost enrollees.
method Markov Chain Monte Carlo methods for clustering diagnostic codes.
result Methodology outperforms common alternatives in health expenditure prediction.
New metrics quantify implementation risk in portfolio backtesting, revealing systematic differences in engine implementations.
problem Systematic divergence in backtested portfolio metrics due to differences in engine implementations.
method Formalized implementation risk, proposed four metrics, executed 15 strategies through five engines, analyzed source-code defects.
result Implementation risk introduces measurable ambiguity in performance attribution, but does not alter investment decisions.
Sparse codes improve optimal control tasks with correlated inputs.
problem Optimal control tasks with correlated feature inputs.
method Used a sparse code to represent natural images in an optimal control task solved with neuro-dynamic programming.
result An over-complete sparse code increases memory capacity and learning speed beyond a complete code.
ACNs learn structured representations by conditioning priors on latent codes.
problem Learning rich, informative latent codes from datasets.
method ACNs use a conditioned prior distribution to model latent codes, reducing coding cost.
result ACNs discover high-level latent features like object class and pose.
New loss function and training scheme improve binary hash codes for better similarity search.
problem Improving binary hash codes for better similarity search tasks.
method Log likelihood loss on Hamming distance target, novel training scheme, multi-indexing.
result Significant improvements in MAP (84%) and query cost reduction for ImageNet and SIFT 1M.
Paper develops a method to create accurate emulators of expensive computer codes.
problem High cost and complexity of running complex computer codes.
method Active learning with Gaussian processes to construct emulators.
result Accurate and compact emulators created for expensive codes.
Neural decoder improves topological code performance.
problem Improving error correction for topological codes.
method Two-step neural network using pseudo-inverse of parity check matrix.
result Outperforms state-of-the-art non-neural decoders for 2D hexagonal color codes.
Transformer models waste resources on long-context tasks.
problem Redundant attention computations in Transformer models for long-context tasks.
method Reformulate sequence modeling as supervised learning, analyze attention sparsity, formulate attention optimization as linear coding problem, propose Dynamic Group Attention.
result DGA reduces computational costs while maintaining performance.
FavMac maximizes value while controlling cost in multi-label prediction.
problem Value-maximizing predictions with strict cost control in multi-label scenarios.
method FavMac pipeline combining any multi-label classifier with online update mechanism.
result FavMac achieves higher value with strict cost control compared to baselines.
Efficient Discrete Supervised Hashing improves cross-modal retrieval by preserving semantic correlations and reducing quantization error.
problem Challenges in preserving semantic correlations and reducing quantization error in cross-modal hashing for large-scale retrieval.
method Collective matrix factorization on heterogenous features and semantic embedding with class labels to learn hash codes efficiently.
result EDSH produces superior performance in both accuracy and scalability over existing methods.
RACER optimizes LLM-as-judge accuracy with dynamic reasoning selection.
problem Balancing reasoning accuracy with computational cost in LLM-as-judge settings.
method Formulates routing as a constrained distributionally robust optimization problem, accounting for distribution shift via KL-divergence uncertainty set.
result RACER achieves superior accuracy-cost trade-offs under distribution shift.
This paper simplifies kernel methods for big datasets.
problem Scaling kernel methods to big datasets.
method Ridge regression and random Fourier features.
result Random Fourier features enable scaling of kernel methods to big datasets with minimal loss in accuracy.
Efficiently learns quantizable embeddings for fast search.
problem Learning binary hamming code representations for search efficiency.
method Directly learns a quantizable embedding representation and sparse binary hash code end-to-end.
result Achieves state-of-the-art search accuracy and significant speedup.
New protocols implement logical gates on encoded qubits with minimal overhead.
problem Efficiently performing universal logical gates on encoded qubits with minimal overhead.
method Using topological codes associated to hyperbolic surfaces, we introduce protocols to implement Dehn twists through constant depth unitary circuits.
result Demonstrated the possibility of applying universal logical gate sets on encoded qubits through constant depth unitary circuits and with constant space overhead.
We define and discuss the first sparse coding algorithm based on closed-form EM updates and continuous latent variables. The underlying generative model consists of a standard `spike-and-slab' prior and a Gaussian noise model. Closed-form solutions for E- and M-step equations are derived by generalizing probabilistic P…
Researchers develop neural optimal transport with Lagrangian costs for efficient computation.
problem Optimal transport between measures with Lagrangian costs for systems with geometric constraints.
method Neural network approach to compute geodesics and optimal transport maps efficiently.
result Efficient computation of geodesics and optimal transport maps without ODE solvers.
PFP-BNNs offer a fast, deterministic approach to Bayesian neural networks.
problem Limited uncertainty handling in traditional neural networks restricts their use in safety-critical settings.
method Probabilistic Forward Pass (PFP) approximates Stochastic Variational Inference (SVI) for efficient BNNs.
result PFP-BNNs achieve up to 4200x speedup over SVI-BNNs while maintaining similar accuracy and uncertainty.
Collage-CNN reduces cloud inference latency by 1.47X with 9X reduced latency variation.
problem Reducing latency variance in cloud machine learning inference.
method Proposes a novel Collage-CNN model that combines multiple images for classification, providing redundancy and cost efficiency.
result Significant reduction in 99th percentile tail latency and variation in inference latency.
New method speeds up sparse Bayesian learning without covariance matrix.
problem Sparse coding problem with uncertainty quantification.
method Covariance-free expectation maximization (CoFEM) that avoids explicit covariance matrix computation.
result Up to thousands of times faster than existing methods without sacrificing accuracy.
We introduce the Randomized Dependence Coefficient (RDC), a measure of non-linear dependence between random variables of arbitrary dimension based on the Hirschfeld-Gebelein-Rényi Maximum Correlation Coefficient. RDC is defined in terms of correlation of random non-linear copula projections; it is invariant with respec…
Classification Ensemble, which uses the weighed polling of outputs, is the art of combining a set of basic classifiers for generating high-performance, robust and more stable results. This study aims to improve the results of identifying the Persian handwritten letters using Error Correcting Output Coding (ECOC) ensemb…
A new algorithm reduces the computational cost of RTRL while maintaining performance.
problem Large computational costs in RTRL for learning long-term dependencies.
method Optimal Kronecker-Sum Approximation (OK) of RTRL.
result OK is optimal for a class of RTRL approximations and matches TBPTT in performance.
New method tackles safe reinforcement learning from offline data.
problem Learn optimal policies from fixed data while adhering to safety constraints.
method Combines offline RL with online optimization to minimize cumulative cost.
result Proves approximate optimality of the approach under certain conditions.
The paper proposes gradient sparsification to reduce communication costs in distributed optimization.
problem Reduction of communication overhead in distributed machine learning.
method Formulates a convex optimization problem to minimize gradient coding length, and proposes simple algorithms for approximate solution.
result The proposed sparsification techniques significantly reduce communication costs without sacrificing accuracy.
Binary embedding of high-dimensional data requires long codes to preserve the discriminative power of the input space. Traditional binary coding methods often suffer from very high computation and storage costs in such a scenario. To address this problem, we propose Circulant Binary Embedding (CBE) which generates bina…
Paper introduces zero-space memory protection for CNNs without ECC overhead.
problem Ensuring reliability of CNNs in safety-critical applications.
method In-place zero-space ECC with weight distribution-oriented training.
result First known zero-space cost memory protection for CNNs.
LSALSA accelerates sparse coding and MCA by learning optimal sparse codes.
problem Efficiently solving sparse coding and MCA problems.
method Deep learning architecture based on SALSA and ADMM.
result LSALSA achieves significant improvements in running time and code quality.
PaGoDA reduces diffusion model training costs by 64x.
problem Diffusion models are computationally expensive during training.
method Three-stage pipeline: downsampled training, distillation, progressive super-resolution.
result PaGoDA achieves state-of-the-art performance with reduced training costs.
ROBEL platform accelerates reinforcement learning with low-cost robots.
problem Accelerating reinforcement learning research in robotics.
method Open-source platform of cost-effective robots for real-world reinforcement learning.
result Robots D'Claw and D'Kitty facilitate learning dexterous manipulation and agile locomotion tasks.