Filter
Exclude
Time range
-
Near
13 May 2025
📘 New Theoretical Framework Drop: Stable & Convexified Information Bottleneck → informationbottleneck.com This work addresses critical instabilities in the classical IB formulation — particularly the non-smooth behavior of p(z|x) under β-phase transitions. ✅ Convexified objective with entropy regularization ✅ Smooth representation flow with no sudden collapse ✅ Symbolic reformulation aligned with mutual information geometry ✅ Compatible with deterministic & variational approximations ✅ Supports continuous β-path tracking (∂L/∂β ∈ C⁰) ✅ Ready for integration in high-dimensional encoders (e.g., ViT, ResNets) Now being applied to symbolic bottlenecks, interpretability flows, and compressed multi-modal fusion. 📎 Read the full theoretical breakdown and join the post-IB evolution. #InformationBottleneck #ConvexOptimization #MutualInformation #DeepLearningTheory #VariationalInference #SymbolicML #RateDistortion #InformationTheory #NeuralCompression #BetaPhaseTransition #RepresentationStability #FarukAlpay #IBFramework #ThermodynamicLearning #DataEncoding #SignalDeformation #LayerwiseCompressibility #IBObjective #AdaptiveRepresentation #PhaseSmoothness #DeterministicBottleneck #XAI #MLFormalism #VariationalBound #JensenGap #NeuralInformationFlow #DifferentiableInformation #InformationTopology #MLTheory #StatisticalLearning #AIResearch

9
3
35
✈️🇸🇬 to #ICLR 2025 🔥🔥🔥 at the iconic city of #Singapore participating in The Thirteenth International Conference on Learning Representations, one of the 4 main #machinelearning #ai conferences worldwide, with Dr @josesanchezhb This year with promissing Invited talks by @dawnsongtweets Song-Chun Zhu @danqi_chen @zicokolter @YiMaTweets @_rockt and 44 workshops, 3827 papers, orals, posters, socials and many more, featuring @SchmidhuberAI @SLapuschkin @lifu_huang @Yoshua_Bengio @sea_snell @wellingmax @svlevine @pabbeel to name a very limited few Thanks to the ICLR organizers: @yisongyue @cvondrick @yuqirose @animesh_garg @orussakovsk @pcastr @francescazfl @savvyRL @fredahshi @SchwinnLeo Jonas Köhler and many others, including the 10s of sponsors like: @Microsoft @AIatMeta @Google @amazon @Oracle @Huawei @Apple @UnitreeRobotics and many others for making it possible one more year. See you all! PD: We will be hosting two @_Qubic_ AGI dinners on the 24th & 25th seats are very limited but DM if you are interested #Artificialntelligence #AI #AGI #RepresentationLearning #FeatureLearning #UnsupervisedLearning #SemiSupervisedLearning #SupervisedLearning #MetricLearning #KernelLearning #SparseCoding #DimensionalityExpansion #HierarchicalModels #OptimalTransport #DeepLearningTheory #Planning #ReinforcementLearning #ComputerVision #NLP #AudioProcessing #SpeechRecognition #Robotics #Neuroscience #Biology #ClimateScience #Sustainability #Fairness #AIethics #Safety #Privacy #Interpretability #ExplainableAI #Visualization #Optimization #TheEndOfKnowledge #Artificiology
7
28
99
4,221
We thank all faculty members and students who participated in the 1st Deep Learning Theory Retreat of TAD Center! We had 2 great days of interesting talks and fruitful discussions. More details: bit.ly/3SIWSZb #deeplearningtheory
2
205
Join us for our last BBS e-Lecture Series talk on Tuesday, 06/07 at 6 PM EST featuring @KrishnaswamyLab! Learn about biological applications to #MachineLearning, #DeepLearningTheory, #DataMining! Register: bit.ly/3rBmYAh
4
4
Unexpected places where you can find research on #DeepLearningTheory: The very interesting paper below (by @maxhfarrell, @LiangTengyuan, and @sanjog_misra) has been published in @ecmaEditors earlier this year. Probably unnoticed by many of us in CS. onlinelibrary.wiley.com/doi/…

11
14 Jun 2020
Replying to @neu_rips
You might take comfort in the fact that there’s a few papers out there working out PAC-Bayes generalisation bounds for some deep net architectures 😉 @roydanroy @bneyshabur @MLpager @felix_biggs @KDziugaite and others #DeepLearningTheory
1
1
3
Awesome new work from @HSompolinsky & friends on manifold de-tangling and deep neural network theory! We're psyched to have him as a speaker at the Deep Math conference this October! (deepmath-conference.com/) #manifolds4life #deeplearningtheory #deepmath2019

1
6
22 Mar 2018
I just released my @MSFTResearch talk on "Neural Homology Theory," work with @rsalakhu! #DeepLearningTheory #AlgebraicTopology Full Talk: youtube.com/watch?v=QDQ9J5E7… Paper: wguss.ml/dev/nht/empirical/
4
36
146
14 Feb 2018
We just released our paper "On Characterizing the Capacity of Neural Networks using Algebraic Topology" on #arxiv. Joint work with @rsalakhu! #DeepLearningTheory #AlgebraicTopology Website: wguss.ml/dev/nht/empirical/ Paper: arxiv.org/abs/1802.04443
9
67
231
5 Feb 2018
I just gave a talk at #Berkeley on some new joint work with @rsalakhu called “Neural Homology Theory.” Expect some exciting developments over the next couple of months! #DeepLearningTheory #algtop
3
14
83
30 Jan 2018
For some reason my most productive days end like this. 📝🗑 I wish adding more layers worked for #DeepLearningTheory too.
7
Great talk by Yuchen Zhang on convexified convnets #ICML17 #deeplearningtheory
8
29