Automatically tunes learning rate and momentum for SGD methods.
problem Manual hyperparameter tuning is costly and lacks theoretical justification.
method Uses statistics of gradient estimator to automatically adjust learning rate and momentum.
result Matches performance of best manual settings for CNN training.
This paper proposes a method to safely adjust exploration in RL to satisfy constraints.
problem Unsafe exploration in reinforcement learning violates constraints on controlled object states.
method Automatic adjustment of exploration inputs and variance-covariance matrix for safety.
result The method guarantees satisfaction of joint chance constraints with specified probability.
LOSSGRAD automatically adjusts learning rates in neural networks.
problem Finding optimal learning rates in gradient descent.
method LOSSGRAD uses quadratic approximation to find locally optimal step-size.
result LOSSGRAD achieves comparable results to other methods while being insensitive to initial learning rate.
Develops a new flexible grid trading model using ANN and SSO.
problem Improving automated trading strategies in financial markets.
method Combines SSO algorithm with ANN for optimizing trading parameters.
result Provides a robust and efficient trading model with better returns.
New mortgage contracts reduce underwater default by adjusting loan balances, but must balance prepayment incentives.
problem Underwater default incentives in mortgages.
method Analyzes automatic balance adjustment and prepayment penalties in mortgage contracts.
result Automatic balance adjustments are preferable to traditional contracts at certain spreads, reducing underwater default.
Automatically adjusts model size for continual Gaussian processes.
problem Determining optimal model size for incremental data.
method Automatic adjustment of model size during continual learning.
result Near-optimal performance across various datasets without hyperparameter tuning.
Proposes GAGA algorithm for automatic hyperparameter learning in signal recovery.
problem Difficulty in selecting hyperparameters in traditional signal recovery methods.
method Global Adaptive Generative Adjustment (GAGA) algorithm for automatic hyperparameter learning and signal estimate.
result Consistency of model selection and signal estimate output.
Implicit Q-learning and SARSA adjust step-sizes automatically, improving stability and performance.
problem Numerical instability and slow progress in Q-learning and SARSA due to step-size calibration.
method Reformulate iterative updates as fixed-point equations, scaling step-sizes inversely with feature norms.
result Implicit methods maintain stability over broader step-size ranges and achieve comparable convergence rates.
Introspects convolutional speech recognition models using Gradient-adjusted Neuron Activation Profiles.
problem Lack of interpretability in deep learning ASR models.
method Gradient-adjusted Neuron Activation Profiles (GradNAPs) for feature and representation visualization.
result Gains insight into how data is processed in convolutional ASR models.
AutoSGD automatically adjusts learning rates for SGD.
problem Inefficient manual learning rate selection for SGD.
method AutoSGD automatically adjusts learning rates based on iteration.
result Empirical results show strong performance across various optimization tasks.
agtboost speeds up gradient tree boosting with automatic complexity adjustment.
problem Speeding up and simplifying gradient tree boosting computations.
method Adaptive gradient tree boosting with automatic complexity adjustment and feature importance.
result Significant decrease in computation time and simplification of model complexity.
Meta-SAC automatically tunes SAC's entropy temperature for better exploration.
problem Exploration-exploitation dilemma in reinforcement learning.
method Meta-SAC uses metagradient and a novel meta objective to automatically adjust SAC's entropy temperature.
result Meta-SAC outperforms SAC-v2 by 10% on the humanoid-v2 task.
Proposes an automatic cyclical scheduling for gradient-based discrete sampling.
problem Gradient-based sampling in high-dimensional models can get stuck in local modes.
method Cyclical step size and balancing schedules with automatic hyperparameter tuning.
result Proves non-asymptotic convergence and inference guarantees for general discrete distributions.
AutoGD automatically adjusts learning rates for gradient descent.
problem Optimizing learning rates for gradient descent methods.
method AutoGD automatically adjusts learning rates based on iteration.
result AutoGD can recover the optimal rate of GD for a broad class of functions.
New methods reduce private federated learning communication automatically.
problem Reducing communication in private federated learning.
method Automatic compression rate adjustment based on training error, using secure aggregation and differential privacy.
result Provable instance-optimal for mean estimation, achieving favorable compression rates.
SALSA automatically adjusts learning rates in stochastic gradient methods.
problem Automatic adjustment of learning rates in stochastic gradient methods.
method SALSA uses a line-search procedure to gradually increase the learning rate, then a statistical test to decrease it.
result SALSA matches the performance of best hand-tuned learning rate schedules in deep learning tasks.
AutoClip automatically adjusts gradient clipping for better audio separation.
problem Improving generalization in audio source separation networks.
method Adaptive gradient clipping based on historical gradient norms.
result Improves generalization performance in audio source separation networks.
Much of the focus in machine learning research is placed in creating new architectures and optimization methods, but the overall loss function is seldom questioned. This paper interprets machine learning from a multi-objective optimization perspective, showing the limitations of the default linear combination of loss f…
A new method automatically and dynamically sets learning rates in deep learning.
problem Determining the appropriate learning rate in deep learning tasks is challenging and often subjective.
method Local Quadratic Approximation (LQA) to automatically and dynamically set learning rates.
result The proposed method leads to nearly optimal learning rates in a computationally efficient way.
We introduce a technique that can automatically tune the parameters of a rule-based computer vision system comprised of thresholds, combinational logic, and time constants. This lets us retain the flexibility and perspicacity of a conventionally structured system while allowing us to perform approximate gradient descen…
A novel neural network training method reduces gradient variance for faster and better reinforcement learning.
problem Improving convergence and generalization in deep reinforcement learning.
method Gradient Monitoring (GM) approach to dynamically adjust the learning process based on feedback.
result The proposed methods, especially AM-WGM, significantly enhance model performance and generalization.
This paper proposes a new randomized strategy for adaptive MCMC using Bayesian optimization. This approach applies to non-differentiable objective functions and trades off exploration and exploitation to reduce the number of potentially costly objective function evaluations. We demonstrate the strategy in the complex s…
Simulation is a useful tool in situations where training data for machine learning models is costly to annotate or even hard to acquire. In this work, we propose a reinforcement learning-based method for automatically adjusting the parameters of any (non-differentiable) simulator, thereby controlling the distribution o…
Bayesian optimisation for dynamically adjusting learning rates in machine learning models.
problem Dynamic adjustment of learning rates schedules in machine learning models.
method Probabilistic model based on latent Gaussian processes and auto-/regressive formulation.
result Flexibly adjusts learning rates schedules to abrupt changes of behaviours.
Aims to optimize influence spread in social networks using bandit algorithms.
problem Maximizing influence spread in unknown social networks.
method Combines Thompson Sampling and Epsilon Greedy algorithms with automatic ensemble learning.
result Demonstrates effectiveness of automatic ensemble learning for combinatorial bandit problems.
A new Metropolis-Hastings algorithm uses Gaussian Processes to speed up sampling from complex models.
problem Sampling from computationally expensive probabilistic models.
method Two-stage Metropolis-Hastings algorithm with a Gaussian Process surrogate model.
result The approach learns the target distribution while sampling, eliminating the need for pre-training.
Python package automates causal parameter estimation using Riesz regression.
problem Efficient estimation of causal and structural parameters.
method Automatic DML and generalized Riesz regression framework.
result Automatic construction of balancing link functions for generalized Riesz regression.
State-of-the-art automatic speech recognition (ASR) systems struggle with the lack of data for rare accents. For sufficiently large datasets, neural engines tend to outshine statistical models in most natural language processing problems. However, a speech accent remains a challenge for both approaches. Phonologists ma…
CAF-HFCM automatically forms a cluster hierarchy and optimizes the number of clusters without trial-and-validation.
problem Challenges in determining the optimal number of clusters in fuzzy c-means.
method CAF-HFCM, an auto-fused hierarchical fuzzy c-means method.
result Automatic agglomeration and optimal number of clusters without validity indices.
In this paper, we design an integrated algorithm to evaluate the sentiment of Chinese market. Firstly, with the help of the web browser automation, we crawl a lot of news and comments from several influential financial websites automatically. Secondly, we use techniques of Natural Language Processing(NLP) under Chinese…
A robust algorithm for forecasting vector time series with seasonal components.
problem Forecasting vector time series with seasonal patterns and handling missing data.
method Auto-regression with seasonal annual, weekly, and daily baselines, and a Gaussian process for residuals. Custom truncated eigendecomposition and low-rank plus block-diagonal Gaussian kernel. Schur complement and Tikhonov regularization for efficient inference.
result The model can scale to very large datasets and is efficient in terms of memory and computation.
Adaptive Prespecification improves precision in randomized trials.
problem Selecting optimal covariates for precision in randomized trials.
method Adaptive Prespecification using V-fold cross-validation and influence curve-squared loss function.
result Substantial gains in precision, equivalent to 20-43% reductions in sample size for the same power.
Study EM and GD for clustering with penalties for misspecification and high dimensions.
problem Clustering with misspecification and high-dimensional data.
method Model-based Gaussian Mixture Models, EM algorithm, GD optimization with AD, penalized likelihood.
result GD outperforms EM on high-dimensional data but both have poor cluster interpretation.
Paper proposes a method to estimate variance reduction in DNN training using importance sampling.
problem Challenges in assessing variance reduction during DNN training using importance sampling.
method Proposes a method for estimating variance reduction using minibatches sampled under importance sampling.
result Demonstrates consistent reduction in variance, improved training efficiency, and enhanced model accuracy.
Variational inference provides a powerful tool for approximate probabilistic in- ference on complex, structured models. Typical variational inference methods, however, require to use inference networks with computationally tractable proba- bility density functions. This largely limits the design and implementation of v…
The performance of stochastic gradient descent (SGD) depends critically on how learning rates are tuned and decreased over time. We propose a method to automatically adjust multiple learning rates so as to minimize the expected error at any one time. The method relies on local gradient variations across samples. In our…
A new method detects anomalies in images without needing model adjustments.
problem Automatic detection of medical image anomalies for radiologists.
method Complementing VAEs with KL-divergence for anomaly localization.
result The method outperforms existing techniques in various settings.
Auto-CEI improves LLM reasoning by balancing assertiveness and conservativeness.
problem Hallucinations and laziness in LLM reasoning tasks.
method Expert Iteration explores reasoning trajectories, guiding incorrect paths back on track and promoting appropriate 'I don't know' responses.
result Auto-CEI achieves superior alignment in logical reasoning, mathematics, and planning tasks.
Proposes a framework to adjust quotes for informational risk in markets with informed traders and price-revealing quotes.
problem Informational risk in markets with informed traders and price-revealing quotes.
method Proposes a tractable framework to adjust quotes considering adverse selection and price reading.
result Market makers can adjust their quotes to better manage informational risk.
SALR improves deep learning generalization by dynamically adjusting learning rates.
problem Improving generalization in deep learning models.
method Sharpness-aware learning rate scheduling based on local loss function sharpness.
result SALR drives solutions to flatter regions, improving generalization and convergence.
In this paper we experimentally analyze the convergence behavior of CoCoA and show, that the number of workers required to achieve the highest convergence rate at any point in time, changes over the course of the training. Based on this observation, we build Chicle, an elastic framework that dynamically adjusts the num…
Automatically designs neural network structure using matrix conditioning.
problem Choosing an effective size and structure of neural networks for new datasets is time-consuming.
method Adjusts neuron proportions and scales network size using matrix conditioning.
result Small networks achieve high accuracy on various datasets.
We introduce a semi-supervised discrete choice model to calibrate discrete choice models when relatively few requests have both choice sets and stated preferences but the majority only have the choice sets. Two classic semi-supervised learning algorithms, the expectation maximization algorithm and the cluster-and-label…
This paper provides estimation and inference methods for the best linear predictor (approximation) of a structural function, such as conditional average structural and treatment effects, and structural derivatives, based on modern machine learning (ML) tools. We represent this structural function as a conditional expec…
The marvel of markets lies in the fact that dispersed information is instantaneously processed and used to adjust the price of goods, services and assets. Financial markets are particularly efficient when it comes to processing information; such information is typically embedded in textual news that is then interpreted…
The idea of computer vision as the Bayesian inverse problem to computer graphics has a long history and an appealing elegance, but it has proved difficult to directly implement. Instead, most vision tasks are approached via complex bottom-up processing pipelines. Here we show that it is possible to write short, simple …
WAVE improves stability in reinforcement learning by adaptively weighting critic's loss.
problem Inherent instability in actor-critic reinforcement learning algorithms.
method Wasserstein adaptive value estimation with Sinkhorn approximation.
result Achieves $\mathcal{O}\left(\frac{1}{k}
ight)$ convergence rate for critic's mean squared error.
TinyCNN accelerates CNN models on embedded FPGA with 15x speedup.
problem Limited memory on embedded FPGAs restricts CNN performance.
method Software and hardware design tool for FPGA resource-aware CNN accelerator.
result 3% accuracy loss with 15.75x speedup on image classification.