The number of possible methods of generalizing binary classification to multi-class classification increases exponentially with the number of class labels. Often, the best method of doing so will be highly problem dependent. Here we present classification software in which the partitioning of multi-class classification…
We introduce and demonstrate a new approach to inference in expressive probabilistic programming languages based on particle Markov chain Monte Carlo. Our approach is simple to implement and easy to parallelize. It applies to Turing-complete probabilistic programming languages and supports accurate inference in models …
Unified framework for adaptive learning systems using consolidation and expansion operations.
problem Managing the balance between consolidating known knowledge and expanding into new evidence in adaptive learning systems.
method Introduces Consolidation-Expansion Operator Mechanics (OpMech) with the order-gap metric to control the balance.
result The order-gap signal provides real-time control and termination guarantees for adaptive learning systems.
NTI models text structure without syntactic trees, improving NLP tasks.
problem Lack of robust syntactic parsing in recursive models.
method Bottom-up tree construction with attention mechanism.
result NTI outperforms state-of-the-art models on NLP tasks.
Self-taught optimizer improves code generation using language models.
problem Improving code generation using language models.
method Recursive self-improvement of a scaffolding program that generates code.
result Improved scaffolding program generates programs with significantly better performance.
Framework for controlling multiple risks in AI models.
problem Enforcing multiple risk constraints in generative AI models.
method Formalizes problem, introduces two dynamic programming algorithms.
result Achieves nearly tight control of all constraint risks under mild assumptions.
Survey of multi-class classification methods and their performance.
problem Generalizing binary classification to multi-class problems.
method Recursive control language to describe partitioning strategies, manual and automatic design.
result One-vs.-one is generally the best solution, but adaptive methods can outperform it in some cases.
Recursive neural networks mimic QCD for jet physics.
problem Improving jet physics predictions using machine learning.
method Analogies between QCD and natural languages for jet clustering.
result Recursive architectures are more accurate and data efficient than previous methods.
Benchmarking recursive collapse claims with a new framework under false-positive control.
problem Evaluating recursive systems for failure patterns and warning claims.
method Developed Loopzero framework for testing recursive failures, specified claim boundaries in Lean, evaluated under FP constraint, and compared with standard detectors.
result No standard detectors or Loopzero's pre-registered quantile detector achieved the required operating point under the false-positive contract.
New algorithm solves Schrödinger bridge problem with mismatched channels.
problem Solving Schrödinger bridge problem with input and noise channel mismatch.
method Design of a Sinkhorn recursion with memory for nonlinear PDEs.
result Demonstrates solving control-affine Schrödinger bridge problem.
Deep learning solves dynamic programming with recursive utility.
problem Challenges in solving high-dimensional discrete-time dynamic programming problems with recursive utility.
method Certainty Equivalent Learning (CEL) algorithm that learns certainty-equivalent value directly with neural networks.
result Accurate value and policy approximations in high-dimensional problems, comparable to VFI in some cases.
The paper investigates model collapse in language models from a probabilistic perspective.
problem Understanding and preventing model collapse in language model training.
method Investigates recursive parametric model training from a probabilistic standpoint, characterizing conditions for model collapse and proposing mitigation strategies.
result Progressively increasing sample size is necessary to prevent model collapse, with a superlinear growth rate required in the asymptotic regime.
Proposes a recursive MPC scheme with probabilistic safety guarantees for uncertain dynamic systems.
problem Probabilistic safety guarantees for MPC in dynamic environments with unknown stochastic agents.
method Uses conformal prediction to derive high-confidence prediction regions and gradually relax safety constraints online.
result Ensures recursive feasibility of MPC schemes by relaxing safety constraints over time.
Adds recursion to deep learning frameworks for better handling of recursive data structures.
problem Lack of support for recursion in existing deep learning frameworks.
method Complements existing frameworks with recursive execution of dataflow graphs and APIs for recursive definitions.
result Recursive implementation reduces training and inference time by more effectively using resources.
Automated translation of mathematical formulae using recursive neural networks.
problem Performing translations between different representations of mathematical formulae.
method Recursive neural networks with multi-variate multi-valued Long Short-Term Memory cells and novel clustering and mini-batch training techniques.
result Achieved a prediction accuracy of 47.05% for predicting symbols at the correct position and 92.3% when ignoring the predicted position.
New approach solves utility maximization problems using Delta family.
problem Utility maximization in stochastic control problems.
method Directly solving DP equation with Delta function representation.
result Explicit series representation of value function.
This work studies the contraction coefficients of Schrödinger bridge problems in linear systems.
problem Optimally controlling the evolution of a system's state density over time.
method Analyzes and improves the convergence rates of dynamic Schrödinger systems via geometric and control-theoretic interpretations.
result New insights into improving computation of worst-case contraction coefficients by preconditioning.
An insurer optimizes investment and risk control with default contagion and regime-switching.
problem Maximizing expected utility of terminal wealth in a risky market with default events.
method Develops a truncation technique to analyze the recursive HJB system and proves the existence and uniqueness of solutions.
result Characterizes optimal trading strategy and risk control for the insurer.
New method for PKM inverse dynamics second derivatives efficiently.
problem Efficient computation of PKM inverse dynamics second derivatives.
method Recursive Lie-group formulation for serial robots adapted to PKM topology.
result Efficient computation of second time derivatives for PKM.
ROTS improves sentence similarity by incorporating structural information.
problem Measuring sentence similarity with theoretical insights and structural awareness.
method Recursive Optimal Transport (ROT) framework to incorporate structural information.
result ROTS outperforms weakly supervised approaches in sentence similarity tasks.
Algorithm discovers dynamic cell structures for better neural network performance.
problem Finding optimal neural network architectures for diverse data samples and time steps.
method Combines recurrent and recursive neural networks to dynamically search for customized cell structures.
result Achieves better prediction accuracy compared to existing models.
CEFOL uses deep learning for dynamic programming with recursive utility.
problem Challenges in solving dynamic programming problems with recursive utility.
method Introduces a separate neural network for certainty equivalent, uses first-order optimality conditions to learn value and policy functions.
result CEFOL achieves high accuracy in learning value and policy functions, matching VFI benchmarks.
Theoretical study on AI models' resilience to data contamination during recursive training.
problem Data contamination in recursive training of generative AI models.
method General framework with minimal assumptions on real data distribution and flexible generative models.
result Contaminated recursive training converges with a rate equal to the minimum of baseline model's rate and contamination fraction.
Recently, deep architectures, such as recurrent and recursive neural networks have been successfully applied to various natural language processing tasks. Inspired by bidirectional recurrent neural networks which use representations that summarize the past and future around an instance, we propose a novel architecture …
Clarifies relation for solving control-affine Schrödinger bridge problems.
problem Solving control-affine Schrödinger bridge problems via Hopf-Cole transform.
method Applies Hopf-Cole transform to conditions of optimality, resulting in nonlinear PDEs.
result Generic control-affine Schrödinger bridge requires further algorithmic development.
ControlVAE improves VAE performance by adding a controller to tune hyperparameters.
problem Existing VAE models struggle with KL vanishing and low reconstruction quality.
method ControlVAE combines a controller inspired by automatic control theory with VAE to improve performance.
result ControlVAE achieves better disentangling and reconstruction quality than existing methods.
GNMR controls runtime stability in low-precision language model training.
problem Efficient low-precision training faces numerical risks at specific operators.
method GNMR compares gradient norms to historical means, applying bounded recovery actions.
result GNMR preserves high-fidelity quality with sparse, budgeted recovery.
Improved MPC with neural networks and active sets for large-scale problems.
problem Large-scale model predictive control with guarantees on feasibility and stability.
method Combines offline-trained neural network and online primal active set solver.
result Achieves 2x reduction in online inference time for large problems.
Study portfolio optimization with transaction costs and recursive preferences.
problem Optimizing portfolios under transaction costs and recursive preferences.
method Recursive preferences, transaction costs, and Merton investment-consumption problem.
result Characterized all parameter combinations for well-posedness of the problem.
A language for specifying complex reinforcement learning tasks.
problem Challenges in specifying and shaping reward functions for complex reinforcement learning tasks.
method Proposes a new language and algorithm for automatically generating and shaping reward functions.
result SPECTRL tool outperforms state-of-the-art baselines.
Unified approach to path planning using probabilistic inference on factor graphs.
problem Path planning problems using probabilistic inference.
method Unified framework using probabilistic factor graphs and message composition rules.
result Unified approach includes various algorithms like Sum-product, Max-product, Dynamic programming, and mixed criteria.
Recursive neural networks improve quark/gluon tagging performance.
problem Improving quark/gluon tagging accuracy using machine learning.
method Recursive neural networks (RecNNs) that embed jet clustering history recursively.
result RecNNs outperform traditional boosted decision tree (BDT) by a few percent in gluon rejection rate.
New method solves uncertain control problems with model uncertainty.
problem Solving uncertain stochastic Markovian control problems in discrete time.
method Adaptive robust control approach using Bellman equation and recursive confidence regions.
result Success of the approach demonstrated through optimal portfolio allocation problem.
Sparseout controls sparsity in neural networks, improving performance in language modeling.
problem Controlling sparsity in neural networks to optimize performance.
method Sparseout is a variant of Dropout that controls sparsity, theoretically proven and empirically validated.
result Sparseout controls the desired level of sparsity in neural network activations, improving performance in language modeling.
The paper proposes a control strategy for systems with sparse parameters using compressed sensing.
problem Control of linear systems with unknown sparse parameters under disturbances.
method Sparse estimation using Recursive Least Squares, improved with Basis Pursuit Denoising, and reformulated probabilistic constraints.
result The proposed algorithm outperforms existing methods in control design for systems with sparse impulse response parameters.
New methodology controls synthetic data bias for neural program synthesis.
problem Deep networks generalize poorly to certain data distributions when trained on synthetic examples.
method Proposes a new methodology to control and evaluate the bias of synthetic data distributions over programs and specifications.
result Training deep networks on controlled synthetic data distributions leads to improved cross-distribution generalization performance.
We present for the first time an asymptotic convergence analysis of two time-scale stochastic approximation driven by `controlled' Markov noise. In particular, both the faster and slower recursions have non-additive controlled Markov noise components in addition to martingale difference noise. We analyze the asymptotic…
Paper develops an efficient online watermark detection for AI-generated text.
problem Detecting AI-generated text from human-written content efficiently.
method Rao-Blackwellized e-processes for anytime-valid inference in streaming generation.
result The method enables recursive token-level evidence updates without storing full history.
Study risk-sensitive reinforcement learning with entropic risk measures and generative models.
problem Risk-sensitive reinforcement learning in discounted MDPs with recursive entropic risk measures.
method Introduced Model-Based ERM Q-Value Iteration (MB-RS-QVI) and derived PAC bounds on sample complexity for value and policy learning. result PAC bounds show exponential dependence on ∣β∣/(1−γ), with tight bounds in S and A. RPSP networks combine PSRs and RNNs for reinforcement learning in POE.
problem Learning in partially observable environments.
method Recurrent filter with PSR, reactive policy, gradient descent.
result RPSP networks outperform memory-preserving models.
Language Rectified Flow improves diffusion language generation by simplifying complex steps.
problem Complexity in diffusion language models limits their implementation in NLP applications.
method Reformulates probabilistic flow models to learn neural ODE models for efficient domain transfer.
result Consistently outperforms baselines on fine-grained control tasks and text editing.
New algorithm solves complex mean-field Schrödinger bridge problem.
problem Designing a controller for diffusion processes with nonlocal interaction.
method Generalized Hopf-Cole transform and Sinkhorn-type algorithm.
result Convergence guarantees for the proposed algorithm under mild assumptions.
Paper develops efficient recursive learning for multi-channel systems with heterogeneous dynamics.
problem Accurately learning system dynamics in complex, multi-channel systems with nonlinear and noisy data.
method Formulates system as Gaussian process state-space models (GPSSMs), introduces heterogeneous multi-output kernel, and develops recursive inference framework.
result Matches SOTA offline GPSSMs in accuracy with 1/100 runtime, and outperforms SOTA online GPSSMs by 70% in accuracy under noise with 1/20 runtime.
Study develops sign recognition system for DHH users.
problem Accessibility of voice-controlled devices for Deaf and Hard-of-Hearing users.
method Multimodal data (RGB video and skeletal data) for sign language recognition using deep learning.
result Validation on GMUASL51 dataset of 12 users and 13107 samples across 51 signs.
The paper tackles data-driven optimal control of unknown nonlinear systems using RKHS.
problem Unknown nonlinear dynamics and stage cost functions.
method Embed state densities into RKHS, learn Markov operators, solve Hamilton-Jacobi-Bellman recursions.
result Solves a wide range of nonlinear control problems, including depth regulation.
Transformer models can solve complex math problems with less data.
problem Solving complex symbolic mathematics problems with limited data.
method Pretrain transformer models on language translation tasks and fine-tune for symbolic math.
result Pretrained transformer models achieve comparable accuracy to state-of-the-art models with less data.
Formal constraints improve RL safety in complex environments.
problem Safety constraints in reinforcement learning for complex environments.
method Specify constraints in formal languages, instantiate as finite automata, augment MDP states, learn dense cost function.
result Improved safety in training RL algorithms over various constraints.
Framework ensures alignment between humans and machines in LLMs.
problem Human-machine misalignment in LLMs scoring mechanisms.
method Lightweight calibration framework for blackbox models.
result Provably guarantees alignment between humans and machines.