Paper proposes a self-training method to generate molecular targets.
problem Challenges in training generative models for complex molecular design.
method Iterative target augmentation using a property predictor and EM iterations.
result Significant gains in molecular design, outperforming previous methods.
A novel framework refines diffusion models iteratively for better downstream reward optimization.
problem Optimizing reward functions during inference of diffusion models.
method Iterative refinement process with noising and reward-guided denoising steps.
result Superior empirical performance in protein and DNA design.
Iterative method learns unknown constraints for MPC control.
problem Learning to satisfy unknown polyhedral state constraints in iterative MPC.
method Collects and improves estimates of unknown constraints using collected data, designs an MPC controller to satisfy the estimated constraints.
result Robust and probabilistic guarantees of constraint satisfaction as a function of task iterations.
Paper analyzes iterates in high-dimensional linear models and proposes estimators for their generalization error.
problem Analyzing iterates in high-dimensional linear models with comparable feature and sample sizes.
method Novel estimators for generalization error, debiasing corrections, and valid confidence intervals.
result Estimators are n \sqrt{n} n -consistent and can be used for early stopping. New approach designs optimal structures using GANs and CNNs.
problem Topology design optimization requires many iterations and is impractical for real-world applications.
method Integrates Generative Adversarial Networks (GANs) and convolutional neural networks for topology design.
result Optimal structures generated effectively and rapidly.
New deep-unfolded network improves video background separation.
problem Video foreground-background separation.
method Deep unfolding of an iterative RPCA algorithm with adaptive learning.
result Proposed network outperforms state-of-the-art in video foreground-background separation.
Bayesian optimization improved for nanophotonic device design.
problem Scalability and derivative information limitations in Bayesian optimization.
method Combining forward shape derivatives and iterative inversion scheme.
result Optimal designs of nanophotonic devices achieved with fewer iterations.
Study improves peptide design efficiency using active and meta-learning.
problem Designing novel functional peptides is inefficient due to low throughput and lack of data.
method Investigated active learning and meta-learning for optimizing peptide design experiments.
result Meta-learning improved average accuracy, but neither method outperformed random choice.
Graph-based NAS improves sample efficiency in architecture design.
problem Current NAS search spaces are static sequences, limiting expressiveness.
method Proposed graph-based search space with vertices and edges for iterative and branching decisions.
result Graph representation improves sample efficiency in architecture design.
Adaptive IP approach optimizes intervention design for causal graph recovery.
problem Designing efficient interventions to recover causal relationships from data.
method Iterative integer programming approach for optimizing information gain.
result Adaptive IP approach achieves full causal graph recovery with fewer interventions.
Paper proposes a new method for designing materials using deep learning.
problem Designing high-performance material distributions from given distributions.
method Iterative process of selecting, generating, and merging material distributions using a deep generative model.
result The method improves material performance through iterative refinement.
Theoretical model for iterative user discovery in recommender systems.
problem Iterative feedback loops in recommender systems and their biases.
method Theoretical framework to model system evolution and convergence properties.
result Theoretical bounds and convergence properties on user discovery and blind spots.
Algorithm estimates sparse signals from linear measurements, improving recovery guarantees.
problem Estimating gradient-sparse signals from noisy linear measurements.
method Iterative alpha expansion with proximal descent and geometric penalty decay.
result Global recovery guarantees under cut-restricted isometry property for Gaussian designs.
Paper proposes a hybrid model-based and data-driven approach for one-bit compressive autoencoding.
problem Designing efficient one-bit compressive autoencoding models for complex systems.
method Hybrid model-based and data-driven methodology for one-bit sparse signal recovery.
result Significant improvement in one-bit compressive autoencoding compared to state-of-the-art algorithms.
Study on discrepancy principle for learning algorithms in nonparametric regression.
problem Determining optimal iteration number in nonparametric regression with unknown optimal iteration.
method Investigates discrepancy principle and modified principles for kernelized spectral filters, using deviation inequalities and change-of-norm arguments.
result Classical discrepancy principle is adaptive for slow rates, while modified principles are adaptive for faster rates.
New algorithm minimizes worst-case regret in uncertain, time-varying dynamics.
problem Model-based policy learning in uncertain, time-varying dynamics.
method Planning regret metric and iterative algorithm for minimizing it.
result Empirical evidence shows the proposed algorithm outperforms existing methods.
Efficient algorithm converges to Nash equilibrium in bilinear problems with bandit feedback.
problem Learning dynamics in bilinear saddle-point problems with bandit feedback.
method Uncoupled learning algorithm combining experimental design and FTRL with a tailored regularizer.
result Last-iterate convergence rate of i l d e O ( T − 1 / 4 ) ilde{O}(T^{-1/4}) i l d e O ( T − 1/4 ) in high probability. Iterative information processing, either based on heuristics or analytical frameworks, has been shown to be a very powerful tool for the design of efficient, yet feasible, wireless receiver architectures. Within this context, algorithms performing message-passing on a probabilistic graph, such as the sum-product (SP) a…
New method explains GNNs using power iteration clustering.
problem Mysterious mechanism of message passing in GNNs.
method Subspace power iteration clustering (SPIC) models.
result Message passing in GNNs can be understood through power iteration.
LES optimizes designs by sampling descent sequences, achieving strong sample efficiency.
problem Optimizing large, complex design spaces is infeasible and unnecessary.
method LES uses Bayesian optimization to target solutions reachable by iterative optimizers.
result LES achieves strong sample efficiency compared to existing methods.
Improves Bayesian optimisation for engineering design problems with many variables.
problem Efficiently searching for global minima in high-dimensional design spaces.
method Integrates input and output data to identify a reduced latent subspace using probabilistic partial least squares.
result Significant improvements in convergence to the global minimum compared to existing methods.
New approach uses hinge loss for iterative regularization in classification.
problem Improving classification accuracy through regularization.
method Develops an iterative regularization approach based on hinge loss.
result Proves convergence and rates of convergence for classification.
New algorithm identifies near-optimal policies in adversarial distributed RL settings.
problem Adversarial agents in distributed RL settings that can collude and report arbitrary data.
method Weighted-Clique algorithm for robust mean estimation from batches, combined with novel distributed algorithms.
result Achieves superior robustness guarantees and near-optimal sample complexities in both offline and online settings.
We propose a conditional non-autoregressive neural sequence model based on iterative refinement. The proposed model is designed based on the principles of latent variable models and denoising autoencoders, and is generally applicable to any sequence generation task. We extensively evaluate the proposed model on machine…
Deep RL improves Diplomacy performance, outperforming previous methods.
problem Applying RL to complex, many-agent, simultaneous-move games like Diplomacy.
method Best response policy iteration and fictitious play approximation.
result Deep RL agents convincingly outperform previous Diplomacy agents.
Poor (even random) starting points for learning/training/optimization are common in machine learning. In many settings, the method of Robbins and Monro (online stochastic gradient descent) is known to be optimal for good starting points, but may not be optimal for poor starting points -- indeed, for poor starting point…
In this paper, we consider the problem of machine teaching, the inverse problem of machine learning. Different from traditional machine teaching which views the learners as batch algorithms, we study a new paradigm where the learner uses an iterative algorithm and a teacher can feed examples sequentially and intelligen…
Proposes a method to generate multivariate prediction intervals for random forests.
problem Uncertainty estimates for iterative design of experiments with multiple correlated model outputs.
method Recalibrated bootstrap method for bagged models.
result Significantly decreases the number of iterations required for satisfactory candidate in sequential learning problems.
New deep learning model improves image deblurring with interpretability.
problem Improving image deblurring performance with neural networks.
method Unrolling iterative algorithm to create a neural network architecture.
result Our deep network outperforms state-of-the-art methods in image deblurring.
Active Inverse Reward Design improves AI agent training by querying users for reward function preferences.
problem Iterative reward function tuning in AI agents is inefficient and may not generalize well.
method Structured queries to the user to compare reward functions, updating posterior with IRD.
result Substantially outperforms IRD in test environments, inferring non-linear rewards.
New framework reduces fault tolerance costs in machine learning.
problem Fault tolerance in iterative-convergent machine learning algorithms.
method Developed a general framework to quantify and design strategies for checkpoint-based fault tolerance.
result SCAR reduces iteration cost of partial failures by 78% - 95%.
Network embedding, which learns low-dimensional vector representation for nodes in the network, has attracted considerable research attention recently. However, the existing methods are incapable of handling billion-scale networks, because they are computationally expensive and, at the same time, difficult to be accele…
This paper considers the problem of solving systems of quadratic equations, namely, recovering an object of interest x ♮ ∈ R n \mathbf{x}^{\natural}\in\mathbb{R}^{n} x ♮ ∈ R n from m m m quadratic equations/samples y i = ( a i ⊤ x ♮ ) 2 y_{i}=(\mathbf{a}_{i}^{\top}\mathbf{x}^{\natural})^{2} y i = ( a i ⊤ x ♮ ) 2 , 1 ≤ i ≤ m 1\leq i\leq m 1 ≤ i ≤ m . This problem, also dubbed as phase retrieval, span…
Improved binary data classification through iterative methods.
problem Efficient inference methods for analyzing compressed binary data.
method Iterative applications of a simple binary data classification framework.
result The iterative method improves classification accuracy.
Neural network ensembles predict design rule violations from early stages of IC design.
problem Predicting design rule violations from placement and global routing stages in IC design.
method Proposes a framework using neural network ensembles with soft voting and PCA-based subset selection.
result Significant improvement in model performance compared to baseline, including better performance than random forest.
Paper connects DP and optimization for RL, suggesting new algorithms.
problem Optimizing scalar objectives in RL.
method Drawing connections between DP and optimization algorithms.
result Links between DP schemes and optimization algorithms.
DeepFPC uses neural networks to recover sparse signals from quantized measurements.
problem Recovering sparse signals from quantized measurements.
method Unfolding the fixed-point continuation algorithm into a deep neural network.
result DeepFPC outperforms state-of-the-art algorithms in DOA estimation.
New RNN reconstructs video frames from sparse measurements.
problem Sequential signal reconstruction from compressive measurements.
method Unfolding proximal gradient method for l1-l1 minimization.
result Outperforms state-of-the-art RNN models in video frame reconstruction.
The design of multiple experiments is commonly undertaken via suboptimal strategies, such as batch (open-loop) design that omits feedback or greedy (myopic) design that does not account for future effects. This paper introduces new strategies for the optimal design of sequential experiments. First, we rigorously formul…
Bayesian optimization improves with transfer learning for aircraft design.
problem Cold start problem in Bayesian optimization for aircraft design.
method Ensemble of surrogate models using transfer learning in a constrained Bayesian optimization framework.
result Significant improvement in convergence and prediction accuracy.
Alternating direction method of multiplier (ADMM) is a popular method used to design distributed versions of a machine learning algorithm, whereby local computations are performed on local data with the output exchanged among neighbors in an iterative fashion. During this iterative process the leakage of data privacy a…
This paper tightens the law of the iterated logarithm for empirical KL_inf, applicable to unbounded data.
problem Developing nonasymptotic concentration bounds for empirical KL_inf with optimal constants and rates.
method Presenting a tight law of the iterated logarithm for empirical KL_inf, applicable to unbounded data.
result A tight law of the iterated logarithm for empirical KL_inf, applicable to unbounded data.
Automates building structural design with reduced mass and carbon footprint.
problem Time-consuming and laborious manual design process for buildings.
method Formulated building structures as graphs, trained end-to-end pipeline with a differentiable simulator.
result Optimal structural designs comparable to GA, with reduced building mass and carbon footprint.
Algorithm optimizes system design and control for better rewards.
problem Optimizing system design and control for maximum rewards.
method Deep reinforcement learning combining policy gradient and model-based optimization.
result DEPS algorithm outperforms state-of-the-art methods in various environments.
FHBI enhances generalization in Bayesian inference with iterative steps in functional spaces.
problem Improving generalization in Bayesian inference models.
method Iterative two-step procedure with adversarial and functional descent steps in a reproducing kernel Hilbert space.
result FHBI consistently outperforms nine baseline methods on the VTAB-1K benchmark.
Two-stage nonconvex algorithm and convex relaxation both achieve optimal accuracy in noisy blind deconvolution.
problem Solving bilinear systems of equations with random noise under different designs.
method Two-stage nonconvex algorithm and convex relaxation.
result Both methods achieve minimax-optimal accuracy in the presence of random noise.
Algorithm design is a laborious process and often requires many iterations of ideation and validation. In this paper, we explore automating algorithm design and present a method to learn an optimization algorithm, which we believe to be the first method that can automatically discover a better algorithm. We approach th…
Automates standards design through machine learning.
problem Manual, time-consuming standards design process.
method Reinforcement learning to optimize proposals.
result Streamlines standards design and innovation.