Develops Bayesian approach for end-to-end learning in stochastic optimization.
problem Stochastic optimization problems under uncertainty.
method Bayesian interpretation and new end-to-end learning algorithms.
result Improved decision maps for empirical risk minimization and distributionally robust optimization.
End-to-end neural network optimizes portfolios by directly learning allocations from features.
problem Error maximization in two-step portfolio optimization.
method Single feed-forward neural network combining prediction and optimization.
result Model-based end-to-end framework achieves Sharpe ratio of 1.16.
Proposes a new method for decision-aware learning in optimization.
problem Contextual linear optimization with cost prediction errors.
method Reweighing prediction error by decision regret for decision-aware predictor.
result Improves over predict-then-optimize framework for misspecified models.
End-to-end portfolio system accounts for model risk.
problem Model risk in portfolio selection.
method Distributionally robust optimization with convex duality.
result Explicitly accounts for model risk in portfolio selection.
Improved portfolio optimization reduces sensitivity to neural network initialization.
problem High sensitivity to neural network initialization in portfolio optimization.
method Robust end-to-end framework for risk budgeting portfolios.
result Enhanced stability in portfolio optimization without compromising performance.
NOVAS uses adaptive stochastic search for non-convex optimization in deep networks.
problem Non-convex optimization challenges in deep neural networks.
method Adaptive stochastic search for non-convex optimization.
result NOVAS outperforms existing alternatives in a structured prediction task.
End-to-end portfolio optimization framework bypassing covariance matrix estimation.
problem Optimizing portfolios with large numbers of assets and constraints.
method Deep learning approach that directly optimizes asset distributions without forecasting.
result Framework outperforms classical methods and handles various constraints.
New algorithm improves causal effect estimation for continuous treatments.
problem Observational causal inference with continuous treatments.
method End-to-end entropy balancing for maximizing causal inference accuracy.
result Our algorithm estimates causal effect more accurately than baseline.
End-to-end training solves deep unsupervised contrastive learning problems.
problem Theoretical analysis of unsupervised contrastive learning.
method End-to-end training of deep neural networks.
result Approximate stationary solutions found for non-convex contrastive loss.
Differentiable perturbed optimizers enable end-to-end learning of discrete decisions.
problem Discrete decisions in machine learning pipelines break back-propagation.
method Transform optimizers into differentiable operations using stochastically perturbed optimizers.
result Smoothness of derivatives can be tuned via noise amplitude.
BPQP improves efficiency of differentiable optimization layers for deep learning.
problem Efficiency in differentiating optimization problems for deep learning models.
method Reformulates optimization problems as quadratic programming, enabling efficient gradient calculation.
result Significant improvement in efficiency (order of magnitude faster) compared to other differentiable optimization layers.
Machine learning is used to compute achievable information rates (AIRs) for a simplified fiber channel. The approach jointly optimizes the input distribution (constellation shaping) and the auxiliary channel distribution to compute AIRs without explicit channel knowledge in an end-to-end fashion.
End-to-end trainable graph matching using improved combinatorial solvers.
problem Graph matching in deep learning.
method Combining deep learning with optimized combinatorial solvers.
result Advances state-of-the-art on deep graph matching benchmarks.
This paper presents KeypointNet, an end-to-end geometric reasoning framework to learn an optimal set of category-specific 3D keypoints, along with their detectors. Given a single image, KeypointNet extracts 3D keypoints that are optimized for a downstream task. We demonstrate this framework on 3D pose estimation by pro…
End-to-end learning refers to training a possibly complex learning system by applying gradient-based learning to the system as a whole. End-to-end learning system is specifically designed so that all modules are differentiable. In effect, not only a central learning machine, but also all "peripheral" modules like repre…
Guided Learning improves end-to-end modeling for multi-stage decision-making.
problem Challenges in training unified neural networks for multi-stage decision-making.
method Guided Learning framework with a guide function and utility function.
result Significant improvement in performance over traditional methods.
End-to-end framework optimizes constrained trajectories using data-driven methods.
problem Optimizing trajectories under constraints with limited dynamics knowledge.
method Data-driven approach decomposes trajectories into function basis, uses maximum a posteriori for optimization, and incorporates linear constraints.
result Commanding results in aeronautics and sailing route optimization.
End-to-end audio recognition system improves accuracy.
problem Improving accuracy in auditory object recognition.
method Proposes an end-to-end deep neural network with an 'inception nucleus' to learn features from raw waveforms.
result Bests current state-of-the-art approaches by 10.4 percentage points on Urbansound8k dataset.
In this paper, we implement an optical fiber communication system as an end-to-end deep neural network, including the complete chain of transmitter, channel model, and receiver. This approach enables the optimization of the transceiver in a single end-to-end process. We illustrate the benefits of this method by applyin…
Paper optimizes KWS models using NAS and quantization for limited resources.
problem Developing efficient keyword spotting models in resource-constrained environments.
method Neural Architecture Search (NAS) for model structure optimization and quantization of weights and activations.
result Achieved high accuracy (95.55%) with minimal parameters and operations using NAS and quantization.
Hybrid model for online nonlinear prediction using LSTM and soft GBDT.
problem Online nonlinear prediction with manual feature selection and model selection issues.
method End-to-end architecture with LSTM for feature extraction and soft GBDT for regression, jointly optimized.
result Significant performance improvements over conventional methods on real datasets.
New benchmark protocol evaluates neural network optimizers for efficiency and data shift sensitivity.
problem Benchmarking neural network optimizers with hyperparameter complexity and data shift sensitivity.
method Proposed a new evaluation protocol combining end-to-end and data-addition training efficiency, using bandit hyperparameter tuning and human study validation.
result No clear winner across all tasks, highlighting the complexity of optimizer performance.
We present differentiable particle filters (DPFs): a differentiable implementation of the particle filter algorithm with learnable motion and measurement models. Since DPFs are end-to-end differentiable, we can efficiently train their models by optimizing end-to-end state estimation performance, rather than proxy objec…
Neural networks struggle with TSP beyond small instances, requiring new approaches.
problem Neural networks struggle to generalize to larger instances of the TSP.
method Unified pipeline to identify inductive biases and promote generalization.
result Zero-shot generalization requires rethinking neural combinatorial optimization.
End-to-end portfolio optimization using quantum annealing for financial decision problems.
problem Optimizing financial portfolios with quantum computing constraints.
method Hybrid pipeline combining quantum and classical optimization.
result Quantum-assisted portfolio optimization can achieve competitive returns.
Survey of methods to train deep architectures without E2EBP.
problem Training deep architectures without end-to-end backpropagation.
method Modular training, weakly modular hybrids.
result Provably optimal alternatives to E2EBP can match or surpass E2EBP performance.
End-to-end policy learning method improves CATE estimation.
problem Learning optimal treatment policies from partially observed data.
method Modified causal forest for policy learning.
result Maximizing policy value is equivalent to minimizing CATE.
Recent studies have introduced end-to-end TTS, which integrates the production of context and acoustic features in statistical parametric speech synthesis. As a result, a single neural network replaced laborious feature engineering with automated feature learning. However, little is known about what types of context in…
DSPO optimizes portfolio construction from raw stock data efficiently.
problem Manual design and misalignment in traditional portfolio construction methods.
method End-to-end neural network framework with Monotonical Logistic Regression loss.
result DSPO constructs optimal sorted portfolios with high performance metrics.
Proposes a machine learning framework for more efficient economic dispatch.
problem Temporal and spatial correlations between system cost and load prediction errors.
method End-to-end machine learning approach with task-specific learning criteria and an efficient optimization kernel.
result Demonstrates the effectiveness and efficiency of the proposed learning framework.
New GP-VAE model improves scalability and performance.
problem Inability of conventional VAEs to model correlations between data points.
method Principled sparse inference approaches to improve scalability of GP-VAEs.
result New model outperforms existing approaches in runtime and memory usage.
New deep learning model optimizes energy use in buildings.
problem Optimizing energy use and comfort in large buildings.
method Transformer-based metamodel trained with simulation and sensor data, calibrated with CMA-ES, optimized with multi-objective algorithms.
result Optimal settings reduce energy loads while maintaining thermal comfort and air quality.
Optimal transport distances help impute missing data.
problem Missing data in real-world datasets.
method Use optimal transport distances as a loss function to impute missing data values.
result OT-based methods match or outperform state-of-the-art imputation methods.
New method learns population dynamics from snapshots using JKO scheme and inverse optimization.
problem Recovering underlying process governing particle evolution from discrete time samples.
method Combines JKO scheme with inverse optimization techniques for end-to-end adversarial training.
result Improved performance over prior JKO-based methods with theoretical guarantees.
Real-world applications often combine learning and optimization problems on graphs. For instance, our objective may be to cluster the graph in order to detect meaningful communities (or solve other common graph optimization problems such as facility location, maxcut, and so on). However, graphs or related attributes ar…
We propose an autoencoding sequence-based transceiver for communication over dispersive channels with intensity modulation and direct detection (IM/DD), designed as a bidirectional deep recurrent neural network (BRNN). The receiver uses a sliding window technique to allow for efficient data stream estimation. We find t…
We propose a novel deep learning method for local self-supervised representation learning that does not require labels nor end-to-end backpropagation but exploits the natural order in data instead. Inspired by the observation that biological neural networks appear to learn without backpropagating a global error signal,…
A new type of End-to-End system for text-dependent speaker verification is presented in this paper. Previously, using the phonetically discriminative/speaker discriminative DNNs as feature extractors for speaker verification has shown promising results. The extracted frame-level (DNN bottleneck, posterior or d-vector) …
New meta-RL method avoids exploration-exploitation trade-off.
problem Learning to explore and exploit simultaneously in meta-RL.
method Developed new objectives for exploration and exploitation.
result DREAM outperforms existing methods on complex tasks.
Connectionist temporal classification (CTC) is widely used for maximum likelihood learning in end-to-end speech recognition models. However, there is usually a disparity between the negative maximum likelihood and the performance metric used in speech recognition, e.g., word error rate (WER). This results in a mismatch…
End-to-end graph-based SSL learns all graph factors dynamically.
problem Learning quality of graph in SSL is crucial but difficult.
method Proposes an end-to-end approach to optimize all graph factors.
result Demonstrates effectiveness on benchmark datasets.
End-to-end kernel learning using generative RFFs for improved performance.
problem Improving kernel learning performance and generalization.
method Develops a generative network via RFFs to implicitly learn the kernel, followed by a linear classifier, jointly trained by ERM.
result Shows superior generalization performance over classical methods in real-world tasks.
Deep learning improves options trading without market assumptions.
problem Traditional options trading requires market dynamics and pricing models.
method End-to-end deep learning approach that learns from market data.
result Deep learning models outperform existing trading strategies.
Deep reinforcement learning approaches have shown impressive results in a variety of different domains, however, more complex heterogeneous architectures such as world models require the different neural components to be trained separately instead of end-to-end. While a simple genetic algorithm recently showed end-to-e…
Structured Prediction Energy Networks (SPENs) are a simple, yet expressive family of structured prediction models (Belanger and McCallum, 2016). An energy function over candidate structured outputs is given by a deep network, and predictions are formed by gradient-based optimization. This paper presents end-to-end lear…
Optimizes decisions without knowing the true distribution using historical data.
problem Optimizing decisions without knowing the true distribution.
method Combines sampling and bisection search algorithms to solve an optimization problem.
result Proves sufficient conditions for local out-of-sample optimality.
We present Caffe con Troll (CcT), a fully compatible end-to-end version of the popular framework Caffe with rebuilt internals. We built CcT to examine the performance characteristics of training and deploying general-purpose convolutional neural networks across different hardware architectures. We find that, by employi…
Autoencoder-based geometric shaping is proposed that includes optimizing bit mappings. Up to 0.2 bits/QAM symbol gain in GMI is achieved for a variety of data rates and in the presence of transceiver impairments. The gains can be harvested with standard binary FEC at no cost w.r.t. conventional BICM.