The abstract explores connections between reinforcement learning, scaling, and diffusion.
problem Aligning reinforcement learning with human feedback and scaling techniques.
method Clarifying connections between reinforcement learning, scaling, and diffusion.
result Introducing a resampling approach for alignment and reward-directed diffusion models.
New insights into cascade feedback linearization of control systems.
problem Obtaining a cascade feedback linearization for invariant control systems.
method Introducing truncated versions of operators from the calculus of variations to prove new theorems.
result Established new geometry and foundational theorems for future work.
Adaptive lateral connections improve visual action recognition.
problem Feedforward neural models lack feedback and lateral connections like the primate visual cortex.
method Dynamic weights in recurrent lateral connections, iteratively reintroduced input.
result Significant performance gains in visual action recognition without pretraining.
Direct feedback alignment reduces data movement in neural networks.
problem Efficiency and energy-efficiency in training large neural networks.
method Sparse feedback matrix for local learning, reducing data movement and compute.
result Orders of magnitude improvement in data movement and 2x improvement in multiply-and-accumulate operations.
Deep networks trained with Hebbian updates perform similarly to back-propagation on image datasets.
problem Training deep networks with realistic asymmetric connections and updates.
method Use Hebbian updates with separate feedforward and feedback weights, and local rule for updates.
result Similar performance to back-propagation achieved with Hebbian updates on challenging image datasets.
Generative replay with feedback connections improves continual learning efficiency.
problem Catastrophic forgetting in artificial neural networks when learning new tasks.
method Split and permuted MNIST tasks, generative replay with distillation, and feedback connections.
result Generative replay with distillation outperformed other methods in all scenarios.
Artificial neural networks are most commonly trained with the back-propagation algorithm, where the gradient for learning is provided by back-propagating the error, layer by layer, from the output layer to the hidden layers. A recently discovered method called feedback-alignment shows that the weights used for propagat…
Proposes CF-SFL to improve sparse data recommendation.
problem Poor performance of CF in sparse data.
method Generative user feedback loop to simulate user feedback.
result Improves recommendation results on multiple datasets.
Graph-based approach repairs programs from diagnostic feedback.
problem Learning to repair programs from limited labeled data and compiler error messages.
method Introduces program-feedback graph and graph neural network for reasoning, and self-supervised learning with unlabeled programs.
result DrRepair significantly outperforms prior work, achieving high repair rates.
New approach detects cyber-attacks in real-time.
problem Real-time detection of cyber-attacks for effective mitigation.
method Aggregates unsupervised anomaly detection algorithms and incorporates delayed feedback.
result Improves anomaly detection performance through theoretical guarantees.
New algorithm improves bandit with graph feedback by decomposing regret.
problem Improving performance in bandit problems with graph feedback.
method Partition-based algorithm framework using regret decomposition.
result Improved and optimal regret bounds on various graph families.
Random Feedback Alignment helps solve low-rank matrix factorization problems.
problem Solving low-rank matrix factorization problems efficiently.
method Random Feedback Alignment (FA) as a bio-plausible alternative to gradient descent.
result FA converges to the optimal solution when the rank of the matrix is at least the rank of the input matrix.
Efficient routing algorithms learn from feedback to minimize path lengths.
problem Optimizing online shortest path routing with end-to-end feedback.
method Adaptive exploration algorithms leveraging networked structure.
result Achieves nearly optimal instance-dependent and worst-case regret for directed acyclic networks.
New graph feedback model for bandits with improved regret bounds.
problem Understanding how graph structure affects regret in bandit problems.
method Introduced fractional weak domination number and k-packing independence number to capture upper and lower bounds on regret. Used strong duality theorem to derive upper and lower bounds. result Proved general upper and lower bounds on regret for various graph structures, showing tightness up to a logarithmic factor.
Skip connections improve biologically-inspired learning rules.
problem Biologically-inspired learning rules often underperform compared to backpropagation.
method Introduced skip connections between intermediate layers in biologically-motivated learning rules.
result Skip connections can match the performance of backpropagation and are robust to hyper-parameters.
We explore whether useful temporal neural generative models can be learned from sequential data without back-propagation through time. We investigate the viability of a more neurocognitively-grounded approach in the context of unsupervised generative modeling of sequences. Specifically, we build on the concept of predi…
Proposes online conformal prediction method with adversarial semi-bandit feedback.
problem Online uncertainty quantification with adversarial semi-bandit feedback.
method Formulates online conformal prediction as an adversarial bandit problem and uses regret minimization.
result Achieves long-run coverage guarantee with adversarial semi-bandit feedback.
ESM-CNN uses error feedback to build a random CNN for time series forecasting.
problem Improving time series forecasting accuracy with CNNs.
method Incrementally adding random filters and neurons to adaptively construct a CNN.
result ESM-CNN outperforms state-of-the-art models in prediction accuracy and efficiency.
Online algorithms stabilize in feedback loops of performative prediction.
problem Feedback loops in algorithmic predictions influence data distributions.
method Martingale argument and randomization to avoid distributional assumptions.
result No-regret algorithms converge to performatively stable equilibria.
This paper introduces a hierarchical associative memory model with multiple layers.
problem Limitations of traditional associative memory models with only one hidden layer.
method Develops a fully recurrent model with arbitrary layers, including locally connected ones, and a corresponding energy function.
result The model can dynamically assemble memories using weights from lower layers and higher layers' rules.
Enhances AI models with human feedback for noisy data.
problem Improving AI model alignment with human feedback in noisy environments.
method Two-stage SL+LHF framework connecting machine learning with human feedback.
result The LNCA ratio identifies conditions for SL+LHF superiority over pure SL.
Photonic co-processor speeds up training of large neural networks.
problem Training large neural networks with backpropagation is inefficient and communication is a bottleneck.
method Direct Feedback Alignment (DFA) with a photonic accelerator.
result Photonic accelerator can compute random projections with trillions of parameters.
Adaptive sampler improves recommendation for implicit feedback data.
problem Challenges in predicting user preferences from implicit feedback data.
method Noisy-label robust learning for adaptive sampler design.
result Significant improvement in recommendation quality on real-world datasets.
New algorithm for online learning with noisy side observations.
problem Online learning with noisy side feedback and graph-structured dependencies.
method Proposes an algorithm using a weighted directed graph to model dependencies and guarantees a regret bound of O(√α* T).
result Guarantees a regret of O(√α* T) after T rounds, where α* is the effective independence number.
Simple algorithms identify best items or full rankings from choice-based feedback.
problem Learning to identify the best item or full ranking from choice-based feedback.
method Nested Elimination (NE) and Nested Partition (NP) algorithms.
result NE is worst-case asymptotically optimal, NP is optimal up to a constant factor.
Sharp sample complexity for multiclass PAC learning with bandit feedback.
problem Multiclass PAC learning with bandit feedback.
method Characterization of optimal sample complexity using a new combinatorial dimension (bandit DS dimension) and a learning algorithm (ListCascade).
result Sharp sample complexity characterization for every concept class up to logarithmic factors.
A simple quantitative example of a reflexive feedback process and the resulting price dynamics after an exogenous price shock to a financial network is presented. Furthermore, an outline of a theory that connects financial reflexivity, which stems from cross-ownership and delayed or incomplete information, and no-arbit…
New algorithm improves distributed SGD with random sparsification for better convergence and generalization.
problem Communication bottleneck in distributed deep learning.
method Proposes detached error feedback (DEF) algorithm to improve convergence and generalization of communication-efficient distributed SGD.
result Shows better convergence and generalization bounds than existing methods.
Paper proposes a combined model for better recommendation by integrating explicit and implicit feedbacks.
problem Improve recommendation accuracy by considering both explicit and implicit feedbacks.
method Developed three models (RHC-PMF, RV-PMF, RHCV-PMF) that incorporate users' explicit and implicit feedbacks for better rating prediction.
result RHCV-PMF model outperforms other models in cold start scenarios for both users and items.
New method learns from either positive or negative feedback alone.
problem Limited applicability of existing preference optimization methods in scenarios with only unpaired feedback.
method Decouples learning from positive and negative feedback, using expectation-maximization (EM) to optimize probability of positive outcomes and explicitly incorporate negative examples.
result Stable learning from negative feedback alone demonstrated.
User preferences for items can be inferred from either explicit feedback, such as item ratings, or implicit feedback, such as rental histories. Research in collaborative filtering has concentrated on explicit feedback, resulting in the development of accurate and scalable models. However, since explicit feedback is oft…
This paper improves image retrieval accuracy through novel relevance feedback methods.
problem Improving image retrieval accuracy in Content-Based Image Retrieval (CBIR).
method Novel addition to feature re-weighting and classification techniques, focusing on 0-th iteration improvement.
result Significantly improved retrieval accuracy from relevance feedback.
Study evaluates new models using human feedback from another model.
problem Evaluate a new model using human feedback collected for another model.
method Formalize problem, propose model-based and model-free estimators, analyze unbiasedness, and empirically evaluate.
result Proposed estimators can predict absolute values, rank, and optimize evaluated policies.
Develops a new model for RLHF accounting for partially observed states and intermediate feedback.
problem Lack of models for partially observed states and intermediate feedback in RLHF.
method PORRL model with cardinal and dueling feedback methods.
result Demonstrates improved learning and alignment with new model-based and model-free methods.
Classifier learns to ignore unreliable feedback from end users.
problem Improving classifier performance by filtering unreliable feedback.
method Modeling end users as autonomous agents, periodically retraining classifier with filtered feedback.
result Classifier can identify and filter out unreliable feedback, improving performance.
Paper characterizes minimax regret rates for online ranking with top-k feedback.
problem Analyzing online ranking with partial feedback.
method Developed techniques from partial monitoring to characterize minimax regret rates.
result Full characterization of minimax regret rates for Precision@n.
Study on sample complexity for pure exploration in feedback graph settings.
problem Sample complexity of pure exploration in online learning with feedback graphs.
method Derive instance-specific lower bounds and present asymptotically optimal algorithm TaS-FG.
result TaS-FG is asymptotically optimal and efficient across different graph configurations.
Study of online learning with noisy feedback in adversarial settings.
problem Adversarial online learning with noisy feedback.
method Models of adversarial online learning with binary losses xored by noise, considering both constant and variable noise rates.
result Tight regret bounds for learning with noise in adversarial online learning.
One-bit feedback suffices for a bandit problem's optimal strategy.
problem Optimal strategy for multi-armed bandit problem with limited feedback.
method Coding and decoding schemes for one-bit feedback to mimic full-reward feedback.
result Regret ratio approaches 1 with one-bit feedback.
Advocates a local feedback approach for RL in unknown systems.
problem Finding optimal feedback laws in unknown nonlinear dynamical systems.
method Searches over a local feedback representation consisting of an open-loop sequence and an optimal linear feedback law.
result Results in highly efficient training and superior performance compared to global methods.
A method corrects feedback shift in predicting conversion rates with delayed feedback.
problem Delayed feedback leads to mislabeling of positive instances in training data.
method Uses importance weight approach to correct feedback shift.
result Proposed method outperforms existing methods in offline and online experiments.
Study how communication and feedback graphs affect learning outcomes.
problem Understanding the impact of feedback graphs on cooperative online learning.
method Analyzed network regret in terms of the independence number of the strong product of communication and feedback graphs.
result Proved bounds for network regret and demonstrated the non-improvable nature of positive results in pathological cases.
New algorithms minimize regret in combinatorial online learning with relative feedback.
problem Minimizing regret in online learning with subset-wise relative preference feedback.
method Instance-dependent and order-optimal regret algorithms for two settings: bounded size subsets and fixed size subsets.
result Regret bounds of O(mnlnT) and O(knlnT) for respective settings. New method uses correlated auxiliary feedback to reduce regret in parameterized bandits.
problem Reducing regret in parameterized bandits with correlated auxiliary feedback.
method Develops a reward estimator using auxiliary feedback with tight confidence bounds.
result Shows significant reduction in regret compared to standard methods.
Test for linearizing 2-input systems with 2D feedback.
problem Linearizability of two-input systems by feedback.
method Algorithmic test for 2D endogenous feedback.
result Systematic derivation of flat outputs.
Reduces user feedback needed for accurate recommender systems.
problem Limited user feedback in recommender systems.
method Partial Bandit and Semi-Bandit approach for efficient user feedback retrieval.
result Similar global accuracy and learning efficiency with reduced feedback.
DeepJSCC-f uses feedback to improve image transmission quality.
problem Improve image transmission quality in feedback channels.
method Autoencoder-based joint source-channel coding (DeepJSCC-f) exploiting feedback.
result Improves reconstruction quality for fixed-length or variable-length transmission.
We present a study on reinforcement learning (RL) from human bandit feedback for sequence-to-sequence learning, exemplified by the task of bandit neural machine translation (NMT). We investigate the reliability of human bandit feedback, and analyze the influence of reliability on the learnability of a reward estimator,…