FRD protects privacy in distributed RL by sharing proxy experience memory.
problem Privacy violation in exchanging experience memory in distributed RL.
method Proposes FRD framework using proxy experience memory.
result Numerical evaluation shows FRD is effective and performance depends on proxy memory structure.
New framework for choosing optimal proxy metrics from past experiments.
problem Difficult to measure long-term treatment effects in experiments.
method Statistical framework to define and construct optimal proxy metrics.
result Optimal proxy metric depends on experiment's sample size.
Image classification with deep neural networks is typically restricted to images of small dimensionality such as 224 x 244 in Resnet models [24]. This limitation excludes the 4000 x 3000 dimensional images that are taken by modern smartphone cameras and smart devices. In this work, we aim to mitigate the prohibitive in…
We use smaller proxy datasets to speed up hyperparameter search.
problem Time-consuming and costly training of neural networks on large datasets.
method Generate smaller 'proxy datasets' by sampling, training on easy/hard examples, or generating synthetic data. Compare proxy quality using variance measures.
result Proxy datasets can explain up to 95% of the variance in full dataset results, significantly faster.
Neural architecture search (NAS) has a great impact by automatically designing effective neural network architectures. However, the prohibitive computational demand of conventional NAS algorithms (e.g. 104 GPU hours) makes it difficult to \emph{directly} search the architectures on large-scale tasks (e.g. ImageNet).…
Develops a method to estimate treatment effects using noisy proxies over time.
problem Estimating individualized treatment effects from noisy proxies of confounders.
method Deconfounding Temporal Autoencoder (DTA) combining autoencoder and causal regularization.
result Improves treatment effect estimates by leveraging noisy proxies and learning hidden confounders.
Study semi-supervised learning with noisy proxy covariates, deriving bounds and showing gains.
problem Learning from noisy proxy covariates with scarce labels.
method Two-stage estimator learning kernel eigenfeatures from all proxy covariates and fitting a ridge predictor on labeled data.
result Finite sample bounds show fast labeled sample rates and consistent gains over supervised and semi-supervised baselines.
Study accelerates NAS research with a large dataset of ZC proxies.
problem Speeding up neural architecture search with ZC proxies.
method Created NAS-Bench-Suite, evaluated 13 ZC proxies across 28 tasks, and provided a unified codebase.
result ZC proxies capture substantial complementary information and can improve NAS algorithm performance.
Estimates proxy-based inference adjustments for distribution shifts.
problem Imperfect proxy data leads to biased inference.
method Empirical calibration of proxy-primary metric discrepancy as a random effect.
result Empowers inference without individual-level response data.
Predicting delayed outcomes is an important problem in recommender systems (e.g., if customers will finish reading an ebook). We formalize the problem as an adversarial, delayed online learning problem and consider how a proxy for the delayed outcome (e.g., if customers read a third of the book in 24 hours) can help mi…
New method recovers latent confounders from high-dimensional proxy variables.
problem Detecting latent confounders from high-dimensional proxy variables.
method Proxy Confounder Factorization (PCF) framework using ICA-PCF and GD-PCF.
result ICA-PCF recovers confounders with high correlation and low error in synthetic and real-world data.
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…
proxymate diagnoses and corrects proxy estimates for reliable inference.
problem Systematic bias in proxy estimates can lead to invalid inference on primary outcomes.
method Four-level framework for proxy validation and adjustment, including diagnostic checks and targeted corrections.
result Facilitated quick decision making on thousands of experiments at Meta.
A data proxy reduces NAS computation cost by preserving key examples.
problem High computation cost in Neural Architecture Search (NAS).
method Measuring example importance based on relative accuracy ranking and creating a data proxy.
result Preserves almost same relative accuracy ranking with 10-20x smaller data proxy.
Proposes a method to create robust linear models with noisy proxies of unobserved variables.
problem Learning robust linear models to handle interventions on unobserved variables with noisy proxies.
method Regularization term that balances in-distribution performance and robustness to interventions.
result Single proxy can create prediction optimal estimators under interventions of bounded strength.
We propose strategies to estimate and make inference on key features of heterogeneous effects in randomized experiments. These key features include best linear predictors of the effects using machine learning proxies, average effects sorted by impact groups, and average characteristics of most and least impacted units.…
Bayesian method estimates causal effects with proxy networks.
problem Estimating causal effects with only proxy measurements of a latent interference network.
method Structural causal model with Block Gibbs sampler and Locally Informed Proposals.
result Accurately estimates causal effects even with noisy proxy networks.
Algorithm identifies best arm with biased proxy and selective ground truth audits.
problem Fixed-confidence best-arm identification with biased proxy and selective ground truth.
method Propensity-weighted estimator and adaptive auditing algorithm.
result Plug-in Neyman rule achieves near-oracle audit efficiency.
Interbank markets are fundamental for bank liquidity management. In this paper, we introduce a model of interbank trading with memory. Our model reproduces features of preferential trading patterns in the e-MID market recently empirically observed through the method of statistically validated networks. The memory mecha…
Bayesian optimization for long-term outcomes using fast and slow experiments.
problem Optimizing long-term system effects with short-term misleading results.
method Combining fast and slow experiments for Bayesian optimization.
result Sequential optimization over large action spaces in a short time.
The paper shows how to use proxy attributes for fairness in machine learning models with missing sensitive group data.
problem Measuring and enforcing fairness in machine learning models with incomplete sensitive group data.
method Using proxy-sensitive attributes to derive upper bounds on multiaccuracy and multicalibration violations and adjust models to satisfy these fairness notions.
result Provable upper bounds on multiaccuracy and multicalibration violations can be derived using proxy-sensitive attributes in the absence of sensitive group data.
PROBE optimizes best-arm identification with cheap proxies, improving sample complexity.
problem Fixed-confidence best-arm identification with costly rewards and correlated cheap proxies.
method PROBE uses control-variate adjustment and phase elimination to learn residual variance online.
result PROBE achieves oracle sample complexity up to a constant factor and additive calibration cost.
The paper explores machine learning methods for proxy modeling in life insurance solvency capital requirements.
problem Life insurance companies need to estimate solvency capital requirements from full loss distributions, but computational limitations restrict full simulations.
method The paper presents various adaptive machine learning approaches to approximate the risk-dependent proxy function using least-squares Monte Carlo.
result The machine learning methods significantly improve the accuracy and efficiency of proxy modeling compared to traditional regression techniques.
Develops a method to audit indirect feature influence in complex models.
problem Auditing indirect feature influence in complex, black-box models.
method Disentangled influence audits using disentangled representations.
result Can detect proxy features and show which ones affect model outcomes most.
New method removes unwanted information from representations efficiently.
problem Learning representations that are uninformative about a target variable.
method Adversarial training with a novel proxy metric for mutual information, leading to an analytically computable approximation.
result Our method effectively removes unwanted information with limited time budget.
A proxy network for few-shot learning improves model generalization.
problem Training models with limited data for new classes.
method Meta-learning architecture with a proxy network that learns class representatives and distance metrics.
result The proxy network outperforms state-of-the-art methods in few-shot learning tasks.
Detects harmful shifts without labels for model performance.
problem Detecting distribution shifts without access to labels.
method Uses a proxy derived from predictions of an error estimator.
result High power and false alarm control under various shifts.
The paper examines how long-memory dynamics, rough-volatility, and persistence affect equity volatility forecasting.
problem The study investigates how long-memory dynamics, rough-volatility, and persistence impact equity volatility forecasting.
method The paper combines semiparametric long-memory estimation, rough-volatility diagnostics, and structured forecasting regressions.
result Persistence measures improve out-of-sample volatility forecasts, particularly during periods of elevated market volatility and in volatility-managed portfolio applications.
A new framework improves VaR recalibration by balancing reliance on imperfect volatility proxies.
problem How to balance reliance on imperfect volatility proxies in one-sided VaR recalibration.
method Proxy-reliance control framework that interpolates between constant-shift and proxy-scaled corrections.
result Lower or intermediate proxy reliance can outperform fully proxy-scaled recalibration in stressed left-tail VaR control.
New method improves treatment effect estimation using autoencoders and causal bridge.
problem Inferring causal effects with unobserved confounders.
method Coupling autoencoder with causal bridge to estimate treatment effects.
result Improves accuracy of treatment effect estimates.
Proxy methods adapt to distribution shifts without explicitly modeling latent confounders.
problem Adapting to distribution shifts under latent variable confounding.
method Proximal causal learning, two-stage kernel estimation.
result Proxy methods outperform other methods in adapting to complex distribution shifts.
Model learns continuously from text without forgetting.
problem Catastrophic forgetting in lifelong language learning.
method Episodic memory with sparse experience replay and local adaptation.
result Model can continuously learn from new datasets.
Experience replay is a key technique behind many recent advances in deep reinforcement learning. Allowing the agent to learn from earlier memories can speed up learning and break undesirable temporal correlations. Despite its wide-spread application, very little is understood about the properties of experience replay. …
Algorithm optimizes biological sequences using bootstrapped training with a score-conditioned generator.
problem Optimizing biological sequences for a black-box score function.
method Bootstrapped training of score-conditioned generator (BootGen) algorithm.
result Our method outperforms competitive baselines on biological sequential design tasks.
PPI uses proxy data to improve inference from limited labels across related tasks.
problem Statistical inference with limited labels across multiple related tasks.
method Prediction-powered inference framework that uses cross-task recalibration to improve power and accuracy.
result Cross-task recalibration can substantially reduce confidence interval widths when labels are scarce.
Unified framework for analyzing neural networks trained by gradient descent.
problem Lack of generalizable guarantees for neural networks trained by gradient descent.
method Proxy convexity and proxy Polyak-Lojasiewicz inequalities.
result Unified guarantees for neural networks trained by gradient descent.
Paper proposes RRD to learn proxy rewards for sparse delayed rewards in episodic reinforcement learning.
problem Learning from sparse and delayed rewards in reinforcement learning.
method Randomized Return Decomposition (RRD) algorithm to redistribute rewards.
result Substantial improvement over baseline algorithms in experiments.
New method improves reliability of selecting individuals based on predicted treatment effects.
problem Reliability of selecting individuals based on predicted conditional average treatment effects (CATE) is unreliable.
method Denoised Conformal Alignment, combining proxy errors, variance estimation, and Benjamini-Hochberg selection.
result Significantly improved power in selecting individuals while maintaining false discovery rate control.
Optimal treatment regime uses proxy variables to improve decision-making.
problem Insufficient covariates in observational data lead to confounding issues.
method Proximal causal inference framework and outcome/treatment confounding bridges.
result The proposed optimal treatment regime outperforms existing ones.
Designing deterministic denominators for SGLD stabilizes large drifts.
problem Stabilizing large drifts in SGLD
method Using state-dependent envelopes and empirical quantiles for activation thresholds
result Proxy-quantile denominators are close to oracle-score behavior and improve deterministic taming choices
FF layers in transformers are nearly as interpretable as sparse autoencoders.
problem Comparing interpretability of feature vectors in FF layers vs. sparse autoencoders.
method Revisited interpretability of FF layers as key-value memories using modern benchmarks.
result FF and SAE feature vectors are similarly interpretable, but FFs can be better in some aspects.
Modern deep reinforcement learning methods have departed from the incremental learning required for eligibility traces, rendering the implementation of the λ-return difficult in this context. In particular, off-policy methods that utilize experience replay remain problematic because their random sampling of minibatch…
DFPV improves PCL for confounded bandit policy evaluation.
problem Estimating causal effects in confounded settings with high-dimensional data.
method Deep feature proxy variable method (DFPV) for high-dimensional, nonlinear relationships.
result DFPV outperforms state-of-the-art methods on synthetic benchmarks and confounded bandit problems.
A framework uses proxies to prioritize treatment without estimating causal effects.
problem Prioritizing treatment when causal effects are hard to estimate.
method Decision-focused framework identifying conditions for proxy usefulness.
result Proxies can recover correct effect ordering under specific conditions.
Single proxy variable helps estimate causal effects from confounders.
problem Estimating causal effects from treatment to outcome when unobserved confounders are present.
method Assumes a single, potentially multi-dimensional proxy variable of the unobserved confounder and a known mechanism generating the proxy from the confounder. Proves causal effects are identifiable under completeness assumption.
result Causal effects are identifiable under SPICE assumption.
The paper studies scaling laws for associative memory mechanisms.
problem Understanding and optimizing learning and memorization processes.
method High-dimensional matrices of outer products of embeddings, relating to transformer models. Derived scaling laws with sample and parameter sizes. Extensive numerical experiments.
result Precise scaling laws and statistical efficiency of estimators.
New method identifies causal effects with categorical unobserved confounders.
problem Estimating causal effects in the presence of unobserved confounders.
method Mixture learning and tensor decomposition for consistent estimation.
result Causal effects are identifiable with categorical unobserved confounders under suitable conditions.
A scalable method for deep metric learning using chance constraints.
problem Improving deep metric learning by addressing feasibility issues.
method Relating DML to chance constraints, reformulating as a feasibility problem, and iteratively training proxies.
result The method effectively improves deep metric learning performance across multiple benchmarks.