George | Abe | Jack | Eva | Cory | |
Coding 1 | Distributed and Federated Learning (Inv) | Array Sensing (Inv) | Machine Learning and Logic (Inv) | Sequential Decision Making (Inv) | |
10:30 AM | Low-complexity posterior matching over the binary symmetric channel with feedback Richard Wesel | Federated representation learning through clustering Erdem Koyuncu | Convergence Analysis of Robust and Sparse M-Estimation of DOA Christoph Mecklenbrauker | Neuro-Symbolic Motivations for Logical Information Theory Alexander Gray | Sequential conformal prediction for time series Yao Xie |
10:50 AM | Deep Learning-based Error Correction Codes for Feedback Channels Alberto Perotti | Analog-digital Scheduling for Federated Learning: A Communication-Efficient Approach Nicolo Michelusi | A new radio to overcome critical link budgets Ralf Müller | Towards a Unification of Logic and Information Theory Luis Lastras | Federated Linear Contextual Bandits with User-level Differential Privacy Jing Yang |
11:10 AM | On graph codes for high-dimensional QKD Lara Dolecek | Distributed learning in networks with delays Hamid Jafarkhani | Direction of Arrival refinement using Wirtinger gradients Peter Gerstoft | Fat Shattering, Joint Measurability, and PAC Learnability of Quantum Hypothesis Classes Abram Magner | Fixed-Budget Differentially Private Best Arm Identification Vincent Tan |
11:30 AM | Low-Latency Decoding of Hypergraph-Product Codes Bane Vasic | Hierarchical Bayes Approach to Personalized Federated Unsupervised Learning Suhas Diggavi | Array-informed waveform design and the role of redundancy Piya Pal | Oracle-Efficient Hybrid Online Learning with Unknown Distribution Changlong Wu | Best arm identification for prompt learning under a limited budget Cong Shen |
Quantum LDPC Codes for Fault-Tolerant Computation (Inv) | Distributed Learning and Optimization | Lloyd Welch: In Memoriam (Inv) | Statistical learning for analysis and design of control systems (Inv) | Info Theory and Wireless | |
1:20 PM | Spatially-Coupled QLDPC Codes Siyi Yang | DIGEST: Fast and Communication Efficient Decentralized Learning with Local Updates Hulya Seferoglu | On the Contributions of Lloyd Welch P Vijay Kumar | Sharp Rates in Dependent Learning Theory: Avoiding Sample Size Deflation for the Square Loss Ingvar Ziemann | A Context-Aware CEO Problem Daewon Seo |
1:40 PM | Fault-Tolerant Quantum Computing with Quantum LDPC Codes Narayanan Rengaswamy | Information aggregation and distributed learning in privacy-critical environments Amin Rahimian | Lloyd Welch and the long life of Reed-Muller codes Stephen Wicker | Toward Trustworthy Reinforcement Learning Lin Yang | Instance-optimality in universal prediction Alankrita Bhatt |
2:00 PM | Concatenated QLDPC Codes and Decoders Nithin Raveendran | AltGDmin-based Fast and Federated Few-Shot Representation Learning Namrata Vaswani | The Baum-Welch algorithm Al Hales | Some Dynamics and Control Perspectives on Policy Gradient Methods Sean Gao | title: Bridging the gap between electromagnetics and array processing Robert Heath |
2:20 PM | Belief Propagation Decoding of Quantum LDPC Codes with Guided Decimation Hanwen Yao | Learning for controls: scalable and adaptable safe controllers Sylvia Herbert | |||
ML Approaches to Info Theory (Inv) | Machine Learning and Control | Wireless Communications | Adversarial Robustness | Coding 2 | |
3:00 PM | Neural Compression with Latice Transform Coding Shirin Saeedi Bidokhti | Sample-Efficient Linear Representation Learning from Non-IID Non-Isotropic Data Nikolai Matni | Golden Modulation: a New and Effective Waveform for Massive IoT Michele Zorzi | A communication-theoretic foundation for robust deep learning? Upamanyu Madhow | Nested Lattice Codes Which Are Cyclic Groups Brian Kurkoski |
3:20 PM | In-Context Estimation using Transformers for Wireless Communications Krishna Narayanan | Distributionally Robust Infinite Horizon Control Babak Hassibi | Matrix Fractional Programming for Integrated Sensing and Communications Wei Yu | Adversarially Robust Learning with Uncertain Perturbation Sets Vinayak Pathak | Improved Belief Propagation Decoding of Polar Codes on Permuted Factor Graphs Hiroshi Kamabe |
3:40 PM | Machine Learning-Aided Channel Coding Hessam Mahdavifar | Wireless Video Streaming with Delayed Client-Feedback: A Constrained Decentralized Team View Vijay Subramanian | OTFS 2.0 (Zak-OTFS) modulation: Near-optimal detection Ananthanarayanan Chockalingam | Low-rank approximation and robustness Vagelis Papalexakis | Simplified Successive Cancellation List Decoding of PAC Codes Hamid Saber |
4:00 PM | Data Driven Approach for Estimating and Achieving Capacity Haim Permuter | The Surprising Power of Denoising Peyman Milanfar | Human-Centered IoT Systems for Privacy and Health Wei Sun | A Goldilocks Cost Constraint Aaron Wagner |
George | Abe | Jack | Eva | Cory | |
Coding | Info Theory 1 | Topics and advances in sequential decision making (Inv) | Machine Learning | Complexity, Causality and Sequences | |
10:30 AM | Enhancing the Error-Floor Performance of LDPC Codes: A Machine Learning Approach Heeyoul Kwak | Zak-OTFS implementation using time and frequency windowing Swaroop Gopalam | Towards instance optimal rates in learning from dependent data Stephen Tu | Theoretical Guarantees of Data Augmented Last Layer Retraining Methods Lalitha Sankar | Pi-Squared: Zero Knowledge Proofs of Mathematical Proofs and their Impact on Verified Computing Sriram Vishwanath |
10:50 AM | High-rate spatially coupled LDPC codes based on convolutional self-orthogonal codes Daniel Costello | Nobody Expects a Differential Equation: Minimum Energy-Per-Bit for the Gaussian Relay Channel with Rank-1 Linear Relaying Oliver Kosut | Experiment Planning with Function Approximation Aldo Pacchiano | Predictive modeling of maternal and neonatal outcomes Ivana Maric | Is it easier to count communities than find them? Cynthia Rush |
11:10 AM | On performance of LDPC codes over block fading channels Dariush Divsalar | Capacity of transmitter Trojans Aria Nosratinia | Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models Quanquan Gu | In-Context Convergence of Transformers Yingbin Liang | Approximate Causal Effect Identification under Weak Confounding Murat Kocaoglu |
11:30 AM | Adaptive coding for large-scale data storage: what, why, and how? Rashmi Vinayak | Consensus Capacity of Noisy Broadcast Channels Neha Sangwan | Transformers Meet Image Denoising: Mitigating Over-smoothing in Transformers via Regularized Nonlocal Functionals Tan Nguyen | Zero-Correlation-Zone Sonar Sequences Hong-Yeop Song | |
Reed-Muller and Polar Codes (Inv) | Info Theory 2 | Individualized Decision Making (Inv) | Deep Learning and Graph Neural Nets | Privacy | |
1:20 PM | Sampling-Based Estimates of Weight Enumerators of Reed-Muller Codes Navin Kashyap | Network Connectivity Information Freshness Tradeoff Sennur Ulukus | Randomization Inference When N Equals One Ben Recht | Distributed Constrained Combinatorial Optimization leveraging Hypergraph Neural Networks Nasimeh Heydaribeni | A New Framework for Designing Polynomial Codes for Problems in Private Information Retrieval Alex Sprintson |
1:40 PM | Error probability bounds for nested sequences of symmetric codes Henry Pfister | Single-letter characterization and undecidability in network information theory Cheuk Ting Li | Online Learning in Bandits with Predicted Context Yongyi Guo | Information theoretic foundations of explainability in graph neural networks Farhad Shirani | Timely offloading of private inferences Anand Sarwate |
2:00 PM | Deep Polar Codes Namyoon Lee | Vertex nomination for influence networks: application to designing microbial communities Alfred Hero | Online Uniform Risk Times Sampling Kyra Gan | Counting graph substructures with graph neural networks Charilaos Kanatsoulis | Private distribution estimation through the lens of combinatorial designs Si-Hyeon Lee |
2:20 PM | GenoWeave: Interleaving Polar Codes Across Strands for DNA Data Storage Hsin-Po Wang | Some families of Jensen-like inequalities with application to information theory Neri Merhav | When Personalization Harms Performance Berk Ustun | Deep Learning based Cryogenic Electron Tomography: Accurate reconstruction and avoiding Hallucinations Reinhard Heckel | Private information retrieval: algebraic construction and combinatorial capacity bounds Ragnar Freij-Hollanti |
Coding Applications | Quantum Info Theory and Algorithms | Reinforcement Learning | Wireless Communications and ML | People-centric ITA (Inv) | |
3:00 PM | New optimal trade-off point for coded caching systems with limited cache size Daniela Tuninetti | Robust and Resource Efficient Quantum Communication over Bosonic Channels Matthieu Bloch | Learning from an exploring demonstrator: Optimal inverse estimation of rewards in bandits Vidya Muthukumar | Sequential alternating least squares approximation (SALSA) for efficient channel estimation in hybrid massive MIMO systems Martin Haardt | Modeling and Correcting Bias in Sequential Evaluation Jingyan Wang |
3:20 PM | Coexistence of eMBB and URLLC in vehicle-to-everything (V2X) communications Homa Nikbakht | Universal framework for simultaneous tomography of quantum states and SPAM noise Abhijith Jayakumar | Rates of Convergence in the Central Limit Theorem for Markov Chains, with an Application to TD Learning R. Srikant | Inductive and Backscatter Techniques for Future IoT David Love | Improving Diversity and Equity in San Francisco School Choice Irene Lo |
3:40 PM | Gradient Coding with Partial Recovery Lalitha Vadlamani | Capacity of Classical Linear Computation over an Elemental Quantum MAC Syed Jafar | Graph Identification for Causal Bandits Urbashi Mitra | Computation Selection: Scheduling Users to Enable Over-the-Air Federated Learning Bobak Nazer | AI and the Future of Optimization Modeling Madeleine Udell |
4:00 PM | Game of Coding: Enabling Decentralized Learning in Trust Minimize d Settings Mohammad Ali Maddah-Ali | Efficient quantum algorithm for solving linear systems in tensor format Marc Vuffray | The Cost of Distributional Robustness in Reinforcement Learning: Minimax-Optimal Sample Efficiency Laixi Shi | Structured Reinforcement Learning for Delay-Optimal Data Transmission in Dense mmWave Networks Jian Li | What is Unique Information, and How do you Use it in Neuroscience (and Fair ML)? Praveen Venkatesh |
George | Abe | Jack | Eva | Cory | |
Distributed Computing and Optimization | Learning and Information Theory (Inv) | Machine Learning | |||
9:00 AM | Distributed Local Sketching for Euclidean Embeddings Neophytos Charalambides | Output-constrained lossy source coding with application to rate-distortion-perception theory Jun Chen | On the Tightness of Information-theoretic Bounds for Generalization Error Jingge Zhu | ||
9:20 AM | Decentralized Sparse Matrix Multiplication Under Byzantine Attacks Joerg Kliewer | Compression of Multisets with Bits-back Coding Ashish Khisti | Teaching Arithmetic to Small Transformers Dimitris Papailiopoulos | ||
9:40 AM | Distributed Structured Matrix Multiplication Derya Malak | Beyond PCA: A Probabilistic Gram-Schmidt Approach to Feature Extraction. Netanel Raviv | Zero-shot sampling of adversarial entities in biomedical question answering Reza Abbasi-Asl | ||
10:00 AM | On Graphs with Finite-Time Consensus and Their Use in Gradient Tracking César Uribe | Quantitative group testing with tunable adaptation Mahdi Soleymani | Towards (environmentally) responsible AI Shaolei Ren | ||
Graduation Day 1 | Graduation Day 2 | Graduation Day 3 | |||
10:40 AM | A Geometric Perspective of Feature Learning Xiangxiang Xu | New algorithms for geometrically approximating massive datasets Naren Manoj | Data Science for Precision Health:Localization and Tracking of Neural Silences in the Brain Alireza Chamanzar | ||
11:00 AM | Generalization and Stability of Interpolating Neural Networks Hossein Taheri | Stochastic variance reduction for min-max optimization Ahmet Alacaoglu | Heterogeneous Models for Network Design and Performance Analysis in Socio-Technical Systems Mansi Sood | ||
11:20 AM | Principled Out-of-Distribution Detection via Multiple Testing Akshayaa Magesh | A first approach to noise-adaptive second-order methods Ali Kavis | Advancing Federated Bandits by Handling Strategical Agents and Harnessing the Power of Federated Learning Chengshuai Shi | ||
11:40 AM | A picture of the space of typical learnable tasks Rahul Ramesh | Estimating the Rate-Distortion Function by Wasserstein Gradient Descent Yibo Yang | Towards Reliable, Scalable and Deployable Millimeter-wave Systems Ish Jain | ||
George | Abe | Jack | Eva | Cory | |
Signal processing and quantum systems (Inv) | High Dimensional Statistics | Differential Privacy | Generative AI | Statistical Learning and Estimation | |
10:30 AM | Maximum Likelihood Quantum Error Mitigation for Algorithms with a Single Correct Output Dror Baron | Binomial Empirical Processe Aryeh Kontorovich | Optimal binary differential privacy via graphs Parastoo Sadeghi | DYffusion: A Dynamics-informed Diffusion Model for Spatiotemporal Forecasting Rose Yu | Data-Driven Estimation of the Optimal Performance of Classifiers via Soft Labels Martina Cardone |
10:50 AM | Theory and applications of hybrid discrete and continuous-variable quantum signal processing Yuan Liu | Kernel Ridge Regression in the Quadratic Regime Yizhe Zhu | Scaling up Private Causal Graph Discovery via Adaptive Privacy Budgeting Ravi Tandon | Adapt and Diffuse: Sample-adaptive Reconstruction via Latent Diffusion Models Mahdi Soltanolkotabi | Time to Model Collapse in Recursive Training Andrew Thangaraj |
11:10 AM | Quantum Signal Processing in Noisy Intermediate-Scale Quantum (NISQ) Devices Victor M. Bastidas | Efficient reductions between some statistical models Ashwin Pananjady | Auditing f-DP in one run Saeed Mahloujifar | The emergence of reproducibility and consistency in diffusion models Qing Qu | Spectral Estimators for Structured Generalized Linear Models via Approximate Message Passing Yihan Zhang |
11:30 AM | Feedback-based quantum algorithms Alicia Magann | On the Noise Sensitivity of the Randomized SVD Elad Romanov | Learning a conditional generative model in total variation Ajil Jalal | Statistical-Computational Trade-offs for Density Estimation Alexandr Andoni | |
Wireless Communications | Control | Private Optimization with Correlated Noise (Inv) | Machine Learning and LLMs | Optimization, Sampling, and Games from Classical Mechanics (Inv) | |
1:20 PM | Fog Learning under Heterogeneity:The Role of Ad-HocWireless Topologies Christopher Brinton | Value of Information: A Novel Metric for Networked Control Systems Tasks John Baras | Overview of Correlated Noise Mechanisms and DP-Follow-the-regularized-leader Abhradeep Guha Thakurta | Implicit Bias of Next-Token Prediction Christos Thrampoulidis | Alternating Mirror Descent for Constrained Min-Max Games Andre Wibisono |
1:40 PM | Achieving optimum received power in the smallest number of steps for discrete-phase RISs Ender Ayanoglu | What network science can offer public health Saswati Sarkar | Correlated Noise Provably Beats Independent Noise for Differentially Private Learning Krishnamurthy Dvijotham | Transformers learn higher-order optimization methods for in-context learning: A study with linear models Vatsal Sharan | Sampling & physics: from classical dynamical system to modern diffusion models Qijia Jiang |
2:00 PM | Hybrid arrays: how many RF chains are required to prevent beam squint? Heedong Do | Controlled sensing for communication-efficient estimation in POMDPs Girish Nair | (Amplified) Banded Matrix Factorization: A unified approach to private training Arun Ganesh | Towards Understanding the Word Sensitivity of Attention Layers: A Study via Random Features Marco Mondelli | Hamiltonian descent and coordinate Hamiltonian descent Jun-Kun Wang |
2:20 PM | Variational Bayes for MIMO detection with unquantized and quantized receptions Duy Nguyen | Transformers for Kalman filtering and control Gautam Goel | Federated Learning of Gboard Language Models with Differential Privacy Zheng Xu | Understanding Self-Distillation and Partial Label Learning in Multi-Class Classification with Label Noise Hye Won Chung | Fast sampling from constrained spaces using the Metropolis-adjusted Mirror Langevin algorithm Ashia Wilson |
Graph Signal Processing (Inv) | Learning/Optimization/Control in Smart Grids (Inv) | Machine Learning and Privacy | Representation Learning | Bandits | |
3:00 PM | Graph filter and GNN design in the presence of graph perturbations Antonio Marques | Learning the Uncertainty Sets of Linear Control Systems via Set Membership: A Non-asymptotic Analysis Yingying Li | The importance of feature preprocessing for differentially private linear optimization Ananda Suresh | Deja-vu: Measuring Memorization in Representation Learning Kamalika Chaudhuri | Global optimization with parametric function approximation: realizability and misspecification Chong Liu |
3:20 PM | Learning Graphs and Simplicial Complexes from Data Geert Leus | Synchro-Waveform Data Analysis in Power Systems Hamed Mohsenian-Rad | All Rivers Run to the Sea: Private Learning with Asymmetric Flows Ramy Ali | Learning Robust Representations: Latent Feature Disentanglement vs Multi-Expert Adversarial Regularization Mostafa El-Khamy | Multi-Fidelity Multi-Armed Bandits Revisited Xuchuang Wang |
3:40 PM | Demystifying and Mitigating Unfairness for Learning over Graphs Yanning Shen | Stability-constrained Reinforcement Learning for Sustainable Energy Systems Yuanyuan Shi | PriorBoost: An Adaptive Algorithm for Learning from Aggregate Responses Adel Javanmard | Learning invariant representations under general interventions on the response Yu Xiang | Approximate Allocation Matching for Structural Causal Bandits with Unobserved Confounders Mahsa Ghasemi |
4:00 PM | Maximizing Reachability in Factored MDPs via Near-Optimal Clustering with Applications to Control of Multi-Agent Systems Bruno Sinopoli | Fast Risk Assessment in Power Grids through Network-aware Gaussian Processes Deepjyoti Deka | Training generative models from privatized data via Entropic Optimal Transport Ayfer Ozgur | Revisiting hard negative sampling for contrastive learning: Optimal representation geometry and neural vs dimensional collapse Shuchin Aeron | Adversarial Attacks on Cooperative Multi-agent Bandits Jinhang Zuo |
George | Abe | Jack | Eva | Cory | |
LLMs and Machine Learning | Machine Learning 1 | Optimization | Coding | Game Theory and Resource Allocation | |
10:30 AM | Attention with Markov: A Framework for Principled Analysis of Transformers via Markov Chains Ashok Vardhan Makkuva | Understanding Hierarchical Representations in Deep Networks via Feature Compression and Discrimination Peng Wang | Operator SVD with neural networks via nested low-rank approximation Jongha (Jon) Ryu | On best short wiretap coset codes Willie Harrison | Port Capacity Leasing Games at Internet Exchange Points Koushik Kar |
10:50 AM | In-Context Learning with Transformers: Softmax Attention Adapts to Function Lipschitzness Aryan Mokhtari | Global Update Tracking: A Decentralized Learning Algorithm for Heterogeneous Data Abolfazl Hashemi | Differentially Privacy Meets Adaptive Optimization Tian Li | Efficient List-decoding of Polynomial Ideal Codes with Optimal List Size Mary Wootters | Market Impacts of Pooling Intermittent Spectrum Randall Berry |
11:10 AM | Provably learning a multi-head attention layer Sitan Chen | Reliable Counterfactual Explanations Under Model Multiplicity Sanghamitra Dutta | Sharp global convergence guarantees for iterative nonconvex optimization with random data Kabir Verchand | Outperforming 5G LDPC codes via Soft Output GRAND Ken Duffy | Incentivizing Secure Software Development: The Role of Liability (Waiver) and Audit Mingyan Liu |
11:30 AM | Regularization and Optimal Multiclass Learning Shaddin Dughmi | Continuous-time neural networks can stably memorize random spike trains Hans-Andrea Loeliger | The landscape and sample complexity of quadratic feasibility Gautam Dasarathy | Online Budgeted Allocation: Worst Case Guarantee and Learning Augmentation Jianyi Yang | |
Large Language Models (Inv) | Neural Nets | Optimization and control in multi-agent systems (Inv) | Coding and Security (Inv) | Machine Learning 2 | |
1:20 PM | Understanding Self-Attention as a Context-Conditioned Markov Chain Samet Oymak | Information-Theoretic Generalization Bounds for Deep Neural Networks Haiyun He | On the Nash Equilibria of Multiplex and Multilayer Network Games Parinaz Naghizadeh | Leveraging AES padding: dBs for nothing and FEC for free in IoT systems Muriel Medard | A unified framework for information-theoretic generalization bounds Maxim Raginsky |
1:40 PM | Language Model Alignment: Theory & Practice Ahmad Beirami | How Transformers Learn Causal Structure with Gradient Descent Jason Lee | Benign Nonconvex Landscapes in Optimal and Robust Control Yang Zheng | Introducing Spice Rafael D'Oliveira | How Uniform Random Weights Induce Non-uniform Bias: Typical Interpolating Neural Networks Generalize with Narrow Teachers Nathan Srebro |
2:00 PM | SpecTr: Fast Speculative Decoding via Optimal Transport Ziteng Sun | Smooth Activations and Reproducibility in Deep Networks Gil Shamir | Logarithmic Communication for Distributed Optimization in Multi-Agent Systems Palma London | CRYPTO-MINE: Cryptanalysis via Mutual Information Neural Estimation Vipindev Adat Vasudevan | Promises and Pitfalls of Threshold-based Auto-labeling Ramya Korlakai Vinayak |
2:20 PM | Watermarking LLMs with Permute-and-Flip Sampling Yu-Xiang Wang | How to Review Peer Reviews? Experiments, Theory and Deployment Nihar Shah | A Theory for Allocating Autonomous Systems Jason Marden | Are activation functions required for learning in all deep networks? Grigorios Chrysos | |
Machine Learning and Efficiency | Adaptive and stochastic optimization (Inv) | Optimization, Control and RL | Communication, Inference and Optimization | ||
3:00 PM | The Expressive Power of Low-Rank Adaptation (LoRA) Kangwook Lee | Trust-Region Sequential Quadratic Programming for Stochastic Optimization with Random Models Mladen Kolar | Data-Driven Control with Inherent Lyapunov Stability Navid Azizan | Remote Inference for Safety Yin Sun | |
3:20 PM | Provable Computational and Sample Efficiency of the Sparse Mixture of Experts Architecture Meng Wang | From Stability to Chaos: Analyzing Gradient Descent Dynamics in Quadratic Regression Krishnakumar Balasubramanian | Robust 1-bit Compressed Sensing with Iterative Hard Thresholding Arya Mazumdar | Clustered Switchback Experiments: Near-Optimal Rates Under Spatiotemporal Interference Su Jia | |
3:40 PM | Efficient Learning of Linear Graph Neural Networks via Node Subsampling Ilan Shomorony | Multiplicative noise and heavy tails in stochastic optimization and machine learning Michael Mahoney | Principled Penalty-based Bilevel Methods for RLHF Tianyi Chen | An interactive control strategy improves information transfer rate in noisy control systems Virginia de Sa | |
4:00 PM | Weight matrix diagnostics and improved neural network training Yaoqing Yang | Why does SGD converge so fast on over-parameterized neural networks? Chaoyue Liu | Model-Free, Regret-Optimal BPI in Online CMDPs Lei Ying | Towards Optimal Distributionally Robust Stochastic Optimization Zaid Harchaoui |